The DOI matches its Crossref record; 265 of the 273 references it cites were found in a registry or an index; 3 of the 95 sources its claims cite were checked for support.
Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects
Open accessAbstract
Data‐driven epoch, the development of machine learning (ML) in materials and device design is an irreversible trend. Its ability and efficiency to handle nonlinear and game‐playing problems is unmatched by traditional simulation computing software and trial‐error experiments. Perovskite solar cells are complex physicochemical devices (systems) that consist of perovskite materials, transport layer materials, and electrodes. Predicting the physicochemical properties and screening the component materials related to perovskite solar cells is the strong point of ML. However, the applications of ML in perovskite solar cells and component materials has only begun to boom in the last two years, so it is necessary to provide a review of the involved ML technologies, the application status, the facing urgent challenges and the development blueprint.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
66 Own interpretation · 58 Sources not found · 31 No basis given · 2 Partly supported · 2 No full text of the sources · 2 Own result · 1 Supported · 1 Own method · accuracy not yet measured
In the paper
“it was found that the structural category descriptors contributed the most to the ML model performance”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.2.2. Transformation of Molecular Descriptors
What the sources say
- Not matchedcites [108] 108. W. Sun, Y. Zheng, K. Yang, Q. Zhang, A. A. Shah, Z. Wu, Y. Sun, L. Feng, D. Chen, Z. Xiao, S. Lu, Y. Li, K. Sun, Sci. Adv. 2019, 5, eaay4275.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirectn = 566- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“Liu et al. [76] built a bandgap database of ABX 3 perovskites and performed bandgap prediction, which further reduced the generalization error of the ML models by refining the types of ABX 3 perovskite”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Data Sources
What the sources say
- Not matchedcites [76] 76. J. Kim, K. Min, Adv. Theory Simul. 2022, 5, 2200068.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“During the training process, the performance of the ML model was greatly improved by increasing the percentage of double perovskite halide data in the training set.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Data Sources
What the sources say
- Not matchedcites [77] 77. A. Jain, G. Hautier, S. P. Ong, K. Persson, J. Mater. Res. 2016, 31, 977.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“found that the effective atomic radius and the number of lone pairs of A-site cations had the greatest effect on the stability of the perovskite phase.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
What the sources say
- Not matchedcites [136] 136. M. Martinez-Arroyo, L. E. Sucar, 18th Int. Conf. on Pattern Recogni- tion (ICPR'06) 2006, 3, 1236.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“Through the comparison of algorithms, it can be seen that the performance of ensemble learning algorithms is better than that of DL.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
What the sources say
- Not matchedcites [136] 136. M. Martinez-Arroyo, L. E. Sucar, 18th Int. Conf. on Pattern Recogni- tion (ICPR'06) 2006, 3, 1236.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Therefore, numerous scholars have tried to incorporate ML in their research process that uses these material properties as training data of ML models to perform target prediction.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.1. The Combination of ML and Perovskite Materials
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As shown in Table 7, the application time of ML in PSCs is significantly later than that in perovskite materials.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.2. The Combination of ML and PSCs
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“second the labels of the studies are very similar, mostly bandgap, formability, stability and PCE.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The data type of most PSCCM studies is tabular data, with very few images and text data.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in Table 7, most studies did not perform model interpretation or only simply performed feature importance analysis, especially when DL was used to build the models.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 85
- It may state two separate claims as one. 46
- The quote only partly states this claim. 1
Every source the paper cites for this claim was checked and supports it.
In the paper
“The test set cannot replace the validation set to perform hyperparameter search because this would lead to overfitting and make the test set lose its ability to evaluate the generalization capability of the model.[148]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Algorithm
What the sources say
- Supportedcites [148] 148. P. BURMAN, Biometrika 1989, 76, 503. source
Section 4.4.1 says validation data are used to select hyperparameters, while test data are left out to assess the final optimized model. It warns that using data for both model development and assessment can cause overfitting and overestimate model accuracy. Section 4.4.2 likewise says the test-set error is a good estimate because the test data were not used in optimization. (LLM, conf=0.93)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Where interpretation and explanations are not uniformly defined and distinguished.[163,164]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5. Model Interpretation
What the sources say
- Supportedcites [163] 163. L. H. Gilpin, D. Bau, B. Z. Yuan, A. Bajwa, M. Specter, L. Kagal, IEEE 5th Int. Conf. on Data Science and Advanced Analytics 2018, 80. https://doi.org/10.1109/dsaa.2018.00018. source
The Introduction (p. 1) says interpretability and explainability have been used interchangeably and argues that they should be distinguished. The Interpretability section (p. 5) also notes the lack of a clear existing definition of interpretability. (LLM, conf=0.93)
- Not matchedcites [164] 164. J.-X. Mi, A.-D. Li, L.-F. Zhou, IEEE Access 2020, 8, 191969.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“They have a similar characteristic that the inner operating mechanism of the models is intuitive, understandable and transparent.[170,171]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.1. Interpretable Algorithmic Model
What the sources say
- Partly supportedcites [170] 170. S. Zheng, C. Ding, Pattern Recogn. Lett. 2020, 131, 227. sourceExperimental — accuracy not yet measured
In “Decision Theory Meets Explainable AI” (Background > Decision Theory; page unavailable), the paper says linear models make importance and utility easy to define, and its Explainable Artificial Intelligence background describes rules as an interpretable form of knowledge. It does not identify GLMs, decision trees, and symbolic regression as a group or say that all three have intuitive, transparent inner mechanisms; it also notes explainability challenges for rule-based systems. (LLM, conf=0.82)
- Not matchedcites [171] 171. Y. Wang, N. Wagner, J. M. Rondinelli, MRS Commun. 2019, 9, 793.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Partly supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, the applications of ML in perovskite solar cells and component materials has only begun to boom in the last two years”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“the power conversion efficiency (PCE) has improved to 25.7% in <10 years.[31]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
What the sources say
- Not matchedcites [31] 31. D.-K. Lee, N.-G. Park, Sol. RRL 2021, 6, 2100455.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“Among them, the average accuracy of the model is lower when SMILES strings are used as input, while the average accuracy of the model is higher when fingerprints of length >1000 bits are used as input.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.2.2. Transformation of Molecular Descriptors
What the sources say
- Not matchedcites [109] 109. A. Mauri, V. Consonni, M. Pavan, R. Todeschini, MATCH Commun. Math. Comput. Chem. 2006, 56, 237.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one. The quote only partly states this claim.
- Not matched
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Third, data collection and regularization are difficult.In our experience, data collection and regularization are not only extremely heavy, accounting for >70% of the entire model building process, but also require the collectors to have extensive knowledge and background related to PSCCM.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“At this stage, the physicochemical and structural data of perovskite materials, the component and performance test data of device-level PSCs are still in a barren and isolated state.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.1. Model Improvement Stage
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“First, the articles that combine ML with PSCCM exploded in the last two years”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Predicting the physicochemical properties and screening the component materials related to perovskite solar cells is the strong point of ML.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Its ability and efficiency to handle nonlinear and game-playing problems is unmatched by traditional simulation computing software and trial-error experiments.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“when the order of magnitude differences of data are too large, data normalization can be used, which can increase the efficiency and accuracy of the model.[75]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Data Sources
What the sources say
- Not matchedcites [75] 75. Y. Liu, W. Yan, H. Zhu, Y. Tu, L. Guan, X. Tan, Org. Electron. 2022, 101, 106426.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“As of today, ML has also been deeply wedged into the materials field.[14][15][16][17][18][19][20][21]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
What the sources say
- Not matchedcites [14] 14. G. R. Schleder, A. C. M. Padilha, C. M. Acosta, M. Costa, A. Fazzio, J. Phys.: Mater. 2019, 2, 032001.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [15] 15. G. H. Gu, J. Noh, I. Kim, Y. Jung, J. Mater. Chem. A 2019, 7, 17096.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [16] 16. G. L. W. Hart, T. Mueller, C. Toher, S. Curtarolo, Nat. Rev. Mater. 2021, 6, 730.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The computational cost of ML is much lower than that of contemporaneous experimental and computational methods.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 1. Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“ML can predict the properties of unknown PSCs from existing data of PSCs, which can accelerate the design and development of PSCs.[55]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 1. Introduction
What the sources say
- Not matchedcites [55] 55. W. Xu, Z. Liu, R. T. Piper, J. W. P. Hsu, Sol. Energy Mater. Sol. Cells 2023, 249, 112055.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“ML, the greatest product of the data-driven epoch, accelerates the process of developing new materials and even bring inspirations that are beyond the reach of human hands and new research perspectives to materials scientists.[26][27][28][29]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
What the sources say
- Not matchedcites [26] 26. Y. Juan, Y. Dai, Y. Yang, J. Zhang, J. Mater. Sci. Technol. 2021, 79, 178.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [27] 27. P. Raccuglia, K. C. Elbert, P. D. F. Adler, C. Falk, M. B. Wenny, A. Mollo, M. Zeller, S. A. Friedler, J. Schrier, A. J. Norquist, Nature 2016, 533, 73.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [28] 28. C. Gao, X. Min, M. Fang, T. Tao, X. Zheng, Y. Liu, X. Wu, Z. Huang, Adv. Funct. Mater. 2021, 32, 2108044.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“Most of the data in the field of PSCCM are tabular data.There are usually no obvious space or time links between features, and the sample volume of the data is small and heterogeneous, which leads to ensemble learning algorithms with trees that typically outperform DL. [122,123]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
What the sources say
- Not matchedcites [122] 122. R. Shwartz-Ziv, A. Armon, Inform. Fusion 2022, 81, 84.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [123] 123. O. Sagi, L. Rokach, WIREs Data Mining Knowl. Discov. 2018, 8, e1249.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“DL belongs to a subset of ML that originated from artificial neural networks and excels to process unstructured data (images, text and sound).[128,129]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
What the sources say
- Not matchedcites [128] 128. R. Miotto, F. Wang, S. Wang, X. Jiang, J. T. Dudley, Briefings in Bioinformatics 2018, 19, 1236.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [129] 129. A. Shrestha, A. Mahmood, IEEE Access 2019, 7, 53040.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“An appropriate amount of experimental and computational data on perovskite solar cells and component materials (PSCCM) already exists, and the related ML technologies are mature.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 1. Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This illustrates that the ML can be applied only when a large amounts of PSCs related data exists, and further supports the importance of the data for the ML models.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.1. Data Sources and Regularization
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This may be due to the fact that the SMILES string is still close to the original information of the data that causes some ML algorithms not to extract hidden features, while longer fingerprints can contain more chemical information making them more unique and easily available for model training.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.2.2. Transformation of Molecular Descriptors
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“The proper extraction of features largely affects the simplicity and generalization capability of the model and the effectiveness of the model interpretation.[78][79][80]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.2.1. Feature Extraction
What the sources say
- Not matchedcites [78] 78. V. Bolón-Canedo, A. Alonso-Betanzos, Inform. Fusion 2019, 52, 1.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [79] 79. P. M. Khan, K. Roy, Expert Opinion on Drug Discovery 2018, 13, 1075.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [80] 80. Y. Li, T. Li, H. Liu, Knowledge and Information Systems 2017, 53, 551.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“The SMILES string and the chemical structure of the molecule are in unique correspondence that can be used as a fingerprint of the chemical structure to express differences of chemical structure, elemental and linkage properties, etc. [107]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.2.2. Transformation of Molecular Descriptors
What the sources say
- Not matchedcites [107] 107. Z.-W. Zhao, M. del Cueto, Y. Geng, A. Troisi, Chem. Mater. 2020, 32, 7777.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“It is no exaggeration that data is the life of the ML models, and even data is more important than the algorithm itself.[57]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.1. Data Sources and Regularization
What the sources say
- Not matchedcites [57] 57. C. Chen, Y. Zuo, W. Ye, X. Li, Z. Deng, S. P. Ong, A Adv. Energy Mater. 2020, 10, 1903242.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For the above-mentioned complicated influencing factors, it is difficult to conduct a comprehensive analysis by a low-cost experimental or computational method.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 1. Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“It avoids the shortcomings inherent in a single model or a model with a single set of parameters, and the final optimized prediction model has strong robustness and anti-overfitting capability.[124,125]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
What the sources say
- Not matchedcites [124] 124. X. Dong, Z. Yu, W. Cao, Y. Shi, Q. Ma, Front. Computer Sci. 2019, 14, 241.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [125] 125. Y. Ren, L. Zhang, P. N. Suganthan, IEEE Comput. Intell. Mag. 2016, 11, 41.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“ML is subtly replacing traditional techniques in numerous fields, such as, biopharmaceuticals, [11] image identification, [12] data mining, [13] etc.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
What the sources say
- Not matchedcites [11] 11. Y. Yang, R. Zhang, Z. Li, L. Mei, S. Wan, H. Ding, Z. Chen, J. Xing, H. Feng, J. Han, H. Jiang, M. Zheng, C. Luo, B. Zhou, J. Med. Chem. 2020, 63, 1337.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [12] 12. A. Esteva, K. Chou, S. Yeung, N. Naik, A. Madani, A. Mottaghi, Y. Liu, E. Topol, J. Dean, R. Socher, npj Digital Med. 2021, 4, 5.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [13] 13. E. A. Olivetti, J. M. Cole, E. Kim, O. Kononova, G. Ceder, T. Y.-J. Han, A. M. Hiszpanski, Appl. Phys. Rev. 2020, 7, 041317.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“The dimensionality reduction of features can enhance the robustness of the model, reduce the computational cost, and remove the noise in the dataset, but this may lose some important information and obscure the meaning of the features, which are mostly used in processing image-type data.[89,90]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.2.1. Feature Extraction
What the sources say
- Not matchedcites [89] 89. M. Lualdi, M. Fasano, J. Proteomics 2019, 198, 18.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [90] 90. T. Zhou, Z. Song, K. Sundmacher, Engineering 2019, 5, 1017.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Molecular fingerprint is now the most commonly used technique for the transformation of molecular descriptors, because it maximally preserves the structural and physicochemical information of the molecule as an input to the ML models.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.2.2. Transformation of Molecular Descriptors
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“It is the third-generation solar cell with the most promising commercialization, [30]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Abstract
What the sources say
- Not matchedcites [30] 30. X. Luo, X. Lin, F. Gao, Y. Zhao, X. Li, L. Zhan, Z. Qiu, J. Wang, C. Chen, L. Meng, X. Gao, Y. Zhang, Z. Huang, R. Fan, H. Liu, Y. Chen, X. Ren, J. Tang, C.-H. Chen, D. Yang, Sci. China: Chem. 2022, 65, 2369.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The choice of suitability algorithm is usually judged by the credibility level on the model, the type (table, image, text, etc.) and volume of data.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“Therefore, the intervention of ML for the study of PSCs may be another promising direction.[53,54]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 1. Introduction
What the sources say
- Not matchedcites [53] 53. Z. Wang, M. Yang, X. Xie, C. Yu, Q. Jiang, M. Huang, H. Algadi, Z. Guo, H. Zhang, Adv. Composites Hybrid Mater. 2022, 5, 2700.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [54] 54. W. Yan, Y. Liu, Y. Zang, J. Cheng, Y. Wang, L. Chu, X. Tan, L. Liu, P. Zhou, W. Li, Z. Zhong, Nano Energy 2022, 99, 107394.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
- Not matched
In the paper
“LIME provides a local explanation for the black box model, that is, it explains the prediction results of a single sample.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [176] 176. S. Lundberg, S.-I. Lee, Adv. Neural Inform. Processing Syst. 2017, 30, 4765.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The performance of the PSCs is influenced by multiple scales and multiple domains of physicochemical features, such as the properties of the material itself, the compatibility between materials, and the structure and fabrication of the PSCs”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.2. The Combination of ML and PSCs
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“At this point, the traditional DFT calculation and simulation methods are no longer applicable in terms of efficiency and performance, whereas ML is the best solution nowadays.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.2. The Combination of ML and PSCs
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The concepts related to model validation and optimization are easily confused, and the application of these techniques is not standardized”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Algorithm
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Optimization of hyperparameters is essential because hyperparameters under the same algorithm can directly affect the performance of the model, which can lead to underfitting or overfitting of the model.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Algorithm
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“SHAP has developed several different explainers for black box models.Among them, TreeExplainer and DeepExplainer are used for ensemble learning and DL respectively.[122,178]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [122] 122. R. Shwartz-Ziv, A. Armon, Inform. Fusion 2022, 81, 84.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [178] 178. J. Klaise, A. Looveren, G. Vacanti, J. Mach. Learn. Res. 2021, 22, 8194.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
In the paper
“Among them, the FA (formamidinium) content plays the most important contribution to the predicted value of PCE, and the high FA content contributes more positively to PCE than the negative contribution when the FA content is low.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [205] 205. A. Mannodi-Kanakkithodi, M. K. Y. Chan, J. Mater. Sci. 2022, 57, 10736.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“In this sample, the model prediction for PCE is 23.53%, and the SHAP explanation shows that the high prediction value is mainly attributed to the high FA content, high hole mobility and suitable bandgap.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Name Description Path
What the sources say
- Not matchedcites [205] 205. A. Mannodi-Kanakkithodi, M. K. Y. Chan, J. Mater. Sci. 2022, 57, 10736.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirectSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For PSC, the role of model interpretation may be more important than model performance, because it can give materials scientists some guidance or inspiration to explore the feature connections and potential causal laws behind complex physicochemical systems.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5. Model Interpretation
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Of course, ML can greatly improve the efficiency of material screening and reduce the computational burden of DFT, which demonstrates the great potential of combining ML and DFT in the field of perovskite materials.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.1. The Combination of ML and Perovskite Materials
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“LIME can be used for the explanation of any black box model and input data, but it also has some drawbacks.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [176] 176. S. Lundberg, S.-I. Lee, Adv. Neural Inform. Processing Syst. 2017, 30, 4765.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“This has a smaller error and more representative of the total sample.[153]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Algorithm
What the sources say
- Not matchedcites [153] 153. D. Krstajic, L. J. Buturovic, D. E. Leahy, S. Thomas, J. Cheminform. 2014, 6, 10.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Performing repeated operations may result in different explanations due to the differences of generated new samples.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The performance of ensemble learning and DL is usually better than classical learning, but their internal working mechanisms also become more complex (e.g., DL uses many nonlinear overlays to improve the performance of the model). [157]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5. Model Interpretation
What the sources say
- Not matchedcites [157] 157. P. P. Angelov, E. A. Soares, R. Jiang, N. I. Arnold, P. M. Atkinson, WIREs Data Mining Knowl. Discov. 2021, 11, e1424.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It only splits the data into training set and test set without setting the validation set, and only performs model training and testing once, so it does not have model optimization ability.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Algorithm
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, it ignores the relationship between features in the generation of new samples, which may lead to the generation of some impossible samples.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, these traditional methods are either less accurate or require a lot of computational resources and time.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.1. The Combination of ML and Perovskite Materials
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The interpretable algorithmic models generally belong to the global interpretation type, namely, they are able to interpret the entire model's operating mechanism based on the complete data set.[167]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5. Model Interpretation
What the sources say
- Not checked — no full text of the sourcecites [167] 167. M. R. Zafar, N. M. Khan, arXiv preprint arXiv:1906.10263, 2019. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The field of PSCCM commonly uses ML to deal with classification and regression problems”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The 67 papers with detailed ML technical descriptions and representation are included in Table 7 and deconstructed in 10 dimensions”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3. Applications of ML in the PSCCM Field
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“But it also leads to the application of ML models in perovskite materials mostly as high-throughput virtual materials screening, which greatly reduces the credibility and practicability of ML models.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.1. The Combination of ML and Perovskite Materials
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
In the paper
“The theory of SHAP explanation is to calculate the cumulative contribution of the features to the predicted values.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [177] 177. H. Chen, S. Lundberg, S.-I. Lee, in Explainable AI in Healthcare and Medicine, (Eds: A. Shaban-Nejad, M. Michalowski, D. L. Buck- eridge), Springer, Cham, Switzerland 2020, 914, 261.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“After that, they used SHAP to explain the model PCE RF .”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [205] 205. A. Mannodi-Kanakkithodi, M. K. Y. Chan, J. Mater. Sci. 2022, 57, 10736.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Compared the screening of virtual perovskite materials by ML model, the parameters of PSCs are easily verified experimentally, which increases the credibility of ML model for application in PSCs.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.2. The Combination of ML and PSCs
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
In the paper
“As shown in Figure 9a, SHAP visualizes the importance ranking of the 13 features and the contribution of each feature.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [205] 205. A. Mannodi-Kanakkithodi, M. K. Y. Chan, J. Mater. Sci. 2022, 57, 10736.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“SR is a representative interpretable ML algorithm that attempts to create optimal mathematical formulations to map the connection between features and predictive targets.[172,173]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.1. Interpretable Algorithmic Model
What the sources say
- Not matchedcites [172] 172. D. A. Augusto, H. J. C. Barbosa, Proc. Sixth Brazilian Symposium on Neural Networks 2000, 1, 173.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [173] 173. G. Peake, J. Wang, Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining 2018, 19.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The interpretation of the model is used to determine whether the model captures valuable features and thus judge whether the model can be transferred to the prediction of other samples, which is significant for small sample databases.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5. Model Interpretation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“There are two main sources of data related to PSC, one is manual experiments or literature collection, and the other is generation by simulation software.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.2. The Combination of ML and PSCs
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Thanks to the massive accumulation of data related to PSCCM, there is space for ML to cut in.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3. Applications of ML in the PSCCM Field
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“SHAP is the most popular explanation method for black box models nowadays, which originated from game theory and was first applied to local and global explanation of black box models in 2017.[177]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5.2. External Explanations of Black-Box Model
What the sources say
- Not matchedcites [177] 177. H. Chen, S. Lundberg, S.-I. Lee, in Explainable AI in Healthcare and Medicine, (Eds: A. Shaban-Nejad, M. Michalowski, D. L. Buck- eridge), Springer, Cham, Switzerland 2020, 914, 261.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
In the paper
“The operational mechanism of the”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5. Model Interpretation
What the sources say
- Not matchedcites [160] 160. M. Sahakyan, Z. Aung, T. Rahwan, IEEE Access 2021, 9, 135392.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
- Rests on an assumption: Model performance is only the result of model decisions, and the reasons for model decisions are sometimes not clear to us.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If the operating mechanism of the model is difficult to understand, it will lead to credibility problems, especially the screening of virtual perovskite materials and the design of new materials.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.5. Model Interpretation
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“In contrast to traditional ML algorithms, it can automatically extract efficient features from unstructured data and train them.[130,131]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 2.3. Selection of Suitability Algorithms
What the sources say
- Not matchedcites [130] 130. S. So, T. Badloe, J. Noh, J. Bravo-Abad, J. Rho, Nanophotonics 2020, 9, 1041.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [131] 131. G. P. Zhang, IEEE Trans. Systems, Man Cybernetics, Part c 2000, 30, 451.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The features of these materials in turn involve thousands of properties such as physical, electronic, structural, morphological, and chemical etc.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“4) The vague model training process, mainly shown that the lack of evaluation of model underfitting and overfitting.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“ML models composed of ensembles learning or DL algorithms generally have better performance for PSCCM, but these complex models are less interpretable, which makes them less credible.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These functional relations may be very important because it may reveal potential physicochemical relations between microscopic features and the attributes of macroscopic target.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.3. ML Inspiration Stage
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“But this problem can be avoided using ML replacement, because the data comes from multiple experimental data and the model will analyze and compare to make the most representative judgment.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.2. ML Replacement Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“The accuracy of the ML model was 82% higher than 70% when using the ideal factor.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.3. ML Applications of PSCCM under Data Barrenness
What the sources say
- Not matchedcites [228] 228. A. Talapatra, B. P. Uberuaga, C. R. Stanek, G. Pilania, Chem. Mater. 2021, 33, 845.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although there are methods that can help to select the number of inputs (see Section 2.2.1), these methods also have limitations, such as not taking into account the potential physicochemical links between features and not being able to select the types of features.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“5) The vague hyperparameter search range.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“1) Overly sparse and unbalanced distribution of training data.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In PSCs, ML is mainly used for feature analysis to find the key features that affect the cell properties and to accelerate and guide the experimental process.Of course, it requires complete feature construction logic and high interpretability of the model.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Step 6: Experimental validation:
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“2) The generalization capability of the model is poor.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“DFT is an important method of generating computational data for perovskite materials, but its computational cost for high-precision data is too high.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.2. ML Replacement Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“There exist various ML algorithms that can the generate functional relations between features and target attributes only from data.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.3. ML Inspiration Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“1) The difficulty of obtaining the inputs is not less than the difficulty of obtaining the labels of the model.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“PSCs are one of the complex physicochemical spaces composed of perovskite materials, the study of ML application in PSCs has important reference value and transfer possibility for other spaces (LED, photodetectors, etc.).”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.2. The Combination of ML and PSCs
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The supplementation of PSCCM data is a long-term project, and it is likely that some of the data are already inadequate (e.g., the information of tandem or large-area PSCs, information of non-toxic perovskite materials, etc.).”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.1. Model Improvement Stage
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Bayesian optimization is an active learning algorithm that allows iterative optimization of the model based on small samples, thus reducing the reliance on high-cost experimental data of PSCCM.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.1. Model Improvement Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“The molecular descriptors generated by the currently used feature transformation tools (see Section 2.2.2) do not represent the full properties of the material, and cannot take into account the requirements of accuracy, speed, and interpretability.[255]”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
What the sources say
- Not matchedcites [255] 255. A. Hernandez, A. Balasubramanian, F. Yuan, S. A. M. Mason, T. Mueller, npj Comput. Mater. 2019, 5, 112.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“4) The predicted target properties can be expressed by a simple function mapping.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“First, these characterization tests usually require the fabrication of complete devices and the devices used in different characterizations are not the same, which results in a waste of experimental resources.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.2. ML Replacement Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“7) The shortage and homogeneity of model interpretation.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“6) Unreasonable evaluation method for model generalization capability, mainly shown that the unreasonable use of training set, validation set and test set.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“3) Unreasonable splitting of training and test sets.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“As shown in Figure 15e, the recombination processes in PSCs are classified into three categories (band-to-band, grain boundary traps, and interfacial traps (Front/Back interface)), which cannot be effectively classified when the conventional ideal factor is used to classify them.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.3. ML Applications of PSCCM under Data Barrenness
What the sources say
- Not matchedcites [228] 228. A. Talapatra, B. P. Uberuaga, C. R. Stanek, G. Pilania, Chem. Mater. 2021, 33, 845.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“PSCs are complex physicochemical systems composed of a variety of materials, including perovskite materials, organic small molecule materials, polymer materials, metal oxides and many other materials with different properties.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“which requires the researcher to have knowledge of both PSCCM and ML fields.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In contrast to traditional experimental methods, the autonomous robotic experimental flow allows for uninterrupted and long experiments without human involvement, and analyze data via ML to optimize the experiments, which brings the possibility of efficient and costeffective experiments.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.2. ML Replacement Stage
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“There is no essential difference between meta-learning and transfer learning.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.1. Model Improvement Stage
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Specifically, the PCE, Voc, Jsc, and FF are closely related for the same PSC, so the knowledge learned in the PCE prediction model can be transferred to the prediction models of Voc, Jsc, and FF.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.1. Model Improvement Stage
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The device-level characterization of PSCs includes a variety of tests, such as electrical performance test, External quantum efficiency (EQE) test, EIS test and stability test.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.2. ML Replacement Stage
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In perovskite materials, the applications of ML are tilted toward the screening of virtual materials, which requires the model to have high generalization capability, and the interpretation and feature analysis of the model are less demanding.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Step 6: Experimental validation:
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is the deconstruction and reconstruction of known materials, which in turn generates new materials that better meet the target requirements.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.3. ML Inspiration Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, for the electrical performance characterization of PSCs with popular components and structures, the test results may not be the same or even test errors may occur due to small differences in each experimenter's skill level and characterization equipment.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.2. ML Replacement Stage
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“3) The fitting of the model requires a large amount of data.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Similarly, it is possible to transfer the inputs used under the same label for similar perovskite materials.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.1. Model Improvement Stage
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Adequate and abundant data of PSCCM is a guarantee for the application of ML into the following two stages.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.1. Model Improvement Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Device-level characterization tests are essentially a mapping between device performance and the properties of the material used, which is close to the concept of ML.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.2. ML Replacement Stage
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Due to the short time of combination between ML and PSCCM, many study steps are incomplete or even unreasonable.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
- Rests on an assumption: The combination between ML and PSCCM has been short.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Unlike high-throughput material screening via ML, ML generation of new component materials of PSC is more purposeful and efficient.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.3. ML Inspiration Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other words, the functional relations between the performance of PSCs and the properties of the component materials are used to help people fully understand the performance of PSCs, and to screen and design new component materials that meet the requirements.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.3. ML Inspiration Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When the target properties are classified more elaborately, the performance of models of that kind will be better, but when the models are used for different kinds of targets, the performance will be greatly reduced.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“2) Overly redundant algorithm comparisons.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 4. Urgent Challenges
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For PSC, ML can generate new passivation/interface materials composed of organic small molecules based on lewis acid-base interactions, and additive materials that improve the growth of perovskite crystals can also be generated based on structural information such as functional groups and chain length.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 5.3. ML Inspiration Stage
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
The paper relies on this without support.
PSC databases are small sample size datasets.
“suitable for small sample size datasets (e.g., PSC databases)”
The paper relies on this without support.
Hold-out (Model Optimization) is rarely used in small sample data sets.
“Hold-out (Model Optimization) is rarely used in small sample data sets.”
The paper relies on this without support.
Model performance is only the result of model decisions, and the reasons for model decisions are sometimes not clear to us.
“model performance is only the result of model decisions, and the reasons for model decisions are sometimes not clear to us.”
The paper relies on this without support.
Interpretable models perform poorly in handling complex classification and regression problems, especially when there are interactions between features of the data.
“Although these models are easy to understand, they perform poorly in handling complex classification and regression problems, especially when there are interactions between features of the data.”
The paper relies on this without support.
The combination between ML and PSCCM has been short.
“Due to the short time of combination between ML and PSCCM, many study steps are incomplete or even unreasonable.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“0.990/16.741/11.737K”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3. Applications of ML in the PSCCM Field
Reported 16.741 · recomputed 137.757169
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Algorithm
“F1-Score is the harmonic mean of Precision and Accuracy.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Algorithm
“F1 Score 1 2 2 F TP TP FP FN = + +”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > Data Sources
“Kim et al. [77] used the Light GBM algorithm model to predict the properties (formation energy, convex hull energy, bandgap) of A 2 BB'X 3 double perovskite.”
§ Machine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects > 3.1. The Combination of ML and Perovskite Materials
“double perovskite structure (A 2 BB'X 6 , AA'BB'X 6 )”
Citations
Cites
Kresse, G., & Furthmüller, J. (1996) · Computational Materials Science · doi:10.1016/0927-0256(96)00008-0 · Cited by 76,871
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Hohenberg, P., & Kohn, W. (1964) · Physical Review · doi:10.1103/physrev.136.b864 · Cited by 53,541
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
Daina, A., Michielin, O., & Zoete, V. (2017) · Scientific Reports · doi:10.1038/srep42717 · Cited by 18,367
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
Jain, A., Ong, S. P., Hautier, G., Chen, W., Richards, W. D., Dacek, S., Cholia, S., Gunter, D., Skinner, D., Ceder, G., et al. (2013) · APL Materials · doi:10.1063/1.4812323 · Cited by 13,094
Research works printed but not linked: 10
- Mauri A., 2006, MATCH Commun. Math. Comput. Chem., 56, 237
- N. K.Chauhan K.Singh in2018 International Conference on Computing Power and Communication Technologies (GUCON) IEEE Piscataway NJ2018 340.
- Freund Y., 1996, Proc. 13th Int. Conf. Machine Learning, 13, 148
- M. R.Zafar N. M.Khan arXiv preprintarXiv:1906.10263 2019.
- D. A.Augusto H. J. C.Barbosa Proc. Sixth Brazilian Symposium on Neural Networks2000 1 173.
- G.Peake J.Wang Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining2018 19.
- Lundberg S., 2017, Adv. Neural Inform. Processing Syst., 30, 4765
- Klaise J., 2021, J. Mach. Learn. Res., 22, 8194
- B.Zhou A.Khosla A.Lapedriza A.Oliva A.Torralba Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2016 2921.
- Bak T., 2022, Int. J. of Precis. Eng. and Manuf.‐Green Tech
Cited by
Sorted by citations
Machine Learning Aided Design and Optimization of Thermal Metamaterials
Zhu, C., Bamidele, E. A., Shen, X., Zhu, G., & Li, B. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00708 · Cited by 208
Wang, C., Cheng, X., Luo, K. H., Nandakumar, K., Wang, Z., Ni, M., Bi, X. T., Zhang, J., & Wang, C. (2025) · Materials Science and Engineering R Reports · doi:10.1016/j.mser.2025.101010 · Cited by 91
Decoding recombination dynamics in perovskite solar cells: an in-depth critical review
Adhikari, R. D., Patel, M. J., Baishya, H., Yadav, D. K., Kalita, M., Alam, M., & Iyer, P. K. (2025) · Chemical Society Reviews · doi:10.1039/d4cs01231c · Cited by 85
Encapsulating perovskite solar cells for long-term stability and prevention of lead toxicity
Dipta, S. S., Rahim, M. A., & Uddin, A. (2024) · Applied Physics Reviews · doi:10.1063/5.0197154 · Cited by 71
Shang, Y., Xiong, Z., An, K., Hauch, J., Brabec, C. J., & Li, N. (2024) · Materials Genome Engineering Advances · doi:10.1002/mgea.28 · Cited by 64
Grandhi, G. K., Jagadamma, L. K., Sugathan, V., Al‐Anesi, B., Manna, D., & Vivo, P. (2023) · Chemical Communications · doi:10.1039/d3cc01881d · Cited by 53
Khan, T. M., & Ahmed, S. R. A. (2024) · Advanced Theory and Simulations · doi:10.1002/adts.202400353 · Cited by 49
Zhang, R., Motes, B. T., Tan, S., Lu, Y., Shih, M.-C., Hao, Y., Yang, K., Srinivasan, S., Bawendi, M. G., & Bulović, V. (2025) · ACS Energy Letters · doi:10.1021/acsenergylett.4c03592 · Cited by 45
The role of machine learning in perovskite solar cell research
Chen, C., Maqsood, A., & Jacobsson, T. J. (2023) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2023.170824 · Cited by 44
Kim, K. S. (2025) · Advanced Energy Materials · doi:10.1002/aenm.202503356 · Cited by 52
Machine learning strategies for small sample size in materials science
Tao, Q., Yu, J., Mu, X., Jia, X., Shi, R., Yao, Z., Wang, C., Zhang, H., & Liu, X. (2025) · Science China Materials · doi:10.1007/s40843-024-3204-5 · Cited by 47
From synthesis to properties: expanding the horizons of machine learning in nanomaterials research
Diao, S., Wu, Q., Li, S., Xu, G., Ren, X., Tan, L., Jiang, G., Song, P., & Meng, X. (2025) · Materials Horizons · doi:10.1039/d4mh01909a · Cited by 42
de la Asunción‐Nadal, V., Sprague, C. I., Guijarro‐Berdiñas, B., Cappel, U. B., & García‐Fernández, A. (2025) · EES solar. · doi:10.1039/d5el00041f · Cited by 51
Akbar, B., Tayara, H., & Chong, K. T. (2024) · iScience · doi:10.1016/j.isci.2024.109200 · Cited by 38
“11,12 15 Salah et al. used ML to reveal electron transport layer (ETL) doping’s critical influence on PSC efficiency across various dataset complexities.”
BackgroundDeep learning for augmented process monitoring of scalable perovskite thin-film fabrication
Laufer, F., Götz, M., & Paetzold, U. W. (2025) · Energy & Environmental Science · doi:10.1039/d4ee03445g · Cited by 43
Machine Learning in Soft Matter: From Simulations to Experiments
Zhang, K., Gong, X., & Jiang, Y. L. (2024) · Advanced Functional Materials · doi:10.1002/adfm.202315177 · Cited by 34
wang, Y., Tan, X., Yang, X., et al. (2025) · Chemical Engineering Journal · doi:10.1016/j.cej.2025.161797 · Cited by 33
Self-citationXu, Z., Chin, S., Park, B., Meng, Y., Kim, S., Han, S., Li, Y., Kim, D., Kim, B.-S., Lee, J., et al. (2024) · Next Materials · doi:10.1016/j.nxmate.2023.100103 · Cited by 35
Gou, F., Ma, Z., Yang, Q., Du, H., Li, Y., Zhang, Q., You, W., Chen, Y., Du, Z., Yang, J., et al. (2025) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c00218 · Cited by 32
Valsalakumar, S., Bhandari, S., Roy, A., Mallick, T. K., Hinshelwood, J., & Sundaram, S. (2024) · npj Computational Materials · doi:10.1038/s41524-024-01383-7 · Cited by 33
Applications of machine learning in surfaces and interfaces
Xu, S., Wu, J., Guo, Y., Zhang, Q., Zhong, X., Li, J., & Ren, W. (2025) · Chemical Physics Reviews · doi:10.1063/5.0244175 · Cited by 32
A scalable and aging-resistant film for radiative cooling
Qi, G., Tan, X., Jiao, Y., Dai, Q., Qiao, Y., Yang, X., Wang, Y., Chen, S., Shi, C., Yan, K., et al. (2024) · Applied Thermal Engineering · doi:10.1016/j.applthermaleng.2024.124310 · Cited by 29
Self-citationMachine learning prediction of materials properties from chemical composition: Status and prospects
Alghadeer, M., Aisyah, N. D., Hezam, M., Alqahtani, S. M., Baloch, A. A. B., & Alharbi, F. H. (2024) · Chemical Physics Reviews · doi:10.1063/5.0235541 · Cited by 31
Liu, H., Yang, A., Zhong, C., Zhu, X., Hao, M., Feng, Z., Tang, J., Chen, Y., Zhang, J., Liu, J., et al. (2025) · ACS Energy Letters · doi:10.1021/acsenergylett.5c00626 · Cited by 32
Machine learning as a characterization method for analysis and design of perovskite solar cells
Liu, Y., Tan, X., Xiang, P., Tu, Y., Shao, T., Zang, Y., Li, X., & Yan, W. (2024) · Materials Today Physics · doi:10.1016/j.mtphys.2024.101359 · Cited by 26
Self-citationKhan, T. M., Saidani, O., & Ahmed, S. R. A. (2024) · RSC Advances · doi:10.1039/d4ra03340j · Cited by 29
Velusamy, A., Yau, S., Liu, C., et al. (2023) · Journal of the Chinese Chemical Society · doi:10.1002/jccs.202300326 · Cited by 26
Yang, A., Sun, Y., Zhang, J., Wang, F., Zhong, C., Chen, Y., Hu, H., Liu, J., & Lin, X. (2024) · Advanced Functional Materials · doi:10.1002/adfm.202410419 · Cited by 27
Surface matrix regulation of perovskite quantum dots for efficient solar cells
Xiao, S., Mei, X., & Zhang, X. (2024) · Energy & Environmental Science · doi:10.1039/d4ee01629g · Cited by 27
Cheng, Z., Liu, J., Jiang, T., Chen, M., Dai, F., Gao, Z., Ke, G., Zhao, Z., & Ou, Q. (2023) · Advanced Optical Materials · doi:10.1002/adom.202301093 · Cited by 26
Dai, Q., Xiang, P., Li, B., et al. (2024) · Chemical Engineering Journal · doi:10.1016/j.cej.2024.155768 · Cited by 24
Self-citationBhatt, P., Pandey, A. K., Rajput, A., Sharma, K. K., Moyez, S. A., & Tewari, A. (2023) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1677 · Cited by 27
Machine learning for perovskite optoelectronics: a review
Lu, F., Liang, Y., Wang, N., Zhu, L., & Wang, J. (2024) · Advanced Photonics · doi:10.1117/1.ap.6.5.054001 · Cited by 27
“42,45,46 Data collection is the foundation of ML, where the key lies in selecting appropriate data sources and ensuring the accuracy of the data.”
BackgroundMechanical stability of flexible perovskite solar cells: challenges, strategies, and prospects
Zhao, H., Wang, Z., Xu, J., et al. (2025) · Journal of Materials Chemistry C · doi:10.1039/d5tc03669k · Cited by 23
Yang, X., Zhou, K., He, X., & Zhang, L. (2024) · Science China Materials · doi:10.1007/s40843-024-2851-9 · Cited by 24
Machine learning-assisted design of high-performance perovskite photodetectors: a review
Li, X. F., Mai, Y., Lan, C., Yang, F., Zhang, P., & Li, S. (2024) · Advanced Composites and Hybrid Materials · doi:10.1007/s42114-024-01113-z · Cited by 25
“…on several metrics, including mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and the coefficient of determination, more commonly referred to as R-squared ( R 2 ), which collectively provide insights into the model’s performance and predictive accuracy [77].”
Touati, S., Benghia, A., Hebboul, Z., Lefkaier, I. K., Kanoun, M. B., & Goumri‐Said, S. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09992-5 · Cited by 24
Superhydrophobic photothermal coatings based on polyurea for durable anti-icing and deicing
Li, X., Tan, X., Tan, X., et al. (2024) · Surfaces and Interfaces · doi:10.1016/j.surfin.2024.105120 · Cited by 21
Self-citationHussain, W., Sawar, S., & Sultan, M. (2023) · RSC Advances · doi:10.1039/d3ra02305b · Cited by 20
Khan, T. M., Hosen, A., Saidani, O., & Ahmed, S. R. A. (2024) · Materials Today Communications · doi:10.1016/j.mtcomm.2024.109639 · Cited by 20
Parametric estimation of photovoltaic systems using a new multi-hybrid evolutionary algorithm
Sharma, P., Saravanakumar, R., Salgotra, R., et al. (2023) · Energy Reports · doi:10.1016/j.egyr.2023.11.012 · Cited by 19
Nishikawa, C., Nishikubo, R., Ishiwari, F., & Saeki, A. (2023) · JACS Au · doi:10.1021/jacsau.3c00519 · Cited by 19
Zhu, C., Liu, Y., Wang, D., Zhu, Z., Zhou, P. C., Tu, Y., Yang, G., Chen, H., Zang, Y., Du, J., et al. (2024) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2024.102321 · Cited by 21
Self-citationMachine learning in X-ray diffraction for materials discovery and characterization
Davel, C. M., Bassiri‐Gharb, N., & Correa‐Baena, J. (2025) · Matter · doi:10.1016/j.matt.2025.102272 · Cited by 25
Zhu, Y., Gao, F., Yi, L., Yi, H., Yu, Q., Zhao, S., Zhou, Y., Wang, Y., & Tang, X. (2025) · Applied Energy · doi:10.1016/j.apenergy.2025.126241 · Cited by 18
Thermodynamic stability descriptor of A2BX6-type perovskite materials
Yang, X., Han, Y., Xu, P., & Liu, F. (2024) · Materials Chemistry and Physics · doi:10.1016/j.matchemphys.2024.130324 · Cited by 20
Interfacial Tuning of Polymeric Composite Materials for High-Performance Energy Devices
Vedhanarayanan, B., Lakshmi, K. C. S., & Lin, T. (2023) · Batteries · doi:10.3390/batteries9100487 · Cited by 19
Zhang, Q., Wang, J., & Liu, G. (2023) · Journal of Energy Chemistry · doi:10.1016/j.jechem.2023.07.018 · Cited by 19
Kaur, N., Pandey, R., & Madan, J. (2024) · Journal of Electronic Materials · doi:10.1007/s11664-024-11266-8 · Cited by 18
“69,70 From the SHAP plot, the position of the X -axis gives the SHAP value, and the Y -axis the feature importance.”
Karade, V. C., Sutar, S. S., Jang, J. H., Gour, K. S., Shin, S. K., Suryawanshi, M. P., Kamat, R. K., Dongale, T. D., Kim, J., & Yun, J. S. (2023) · Crystals · doi:10.3390/cryst13111581 · Cited by 18
“Machine learning (ML) has found promising applications in photovoltaic (PV) technology, offering opportunities to enhance PCE, reduce costs, and optimize performance [17,18].”
BackgroundZhao, S., Zhou, S., Guo, Z., Luo, H., Jiang, Z., Lin, N., Chen, M., Li, L., & Li, C. (2025) · ACS Sustainable Chemistry & Engineering · doi:10.1021/acssuschemeng.5c01361 · Cited by 21
Reza, M. S., Ghosh, A., Shimul, A. I., Nabil, S. H., Akter, M., Chaudhry, A. R., Sobuj, D. R., Kumar, Y. A., Biswas, S., Alam, K., et al. (2025) · Materials Advances · doi:10.1039/d5ma00955c · Cited by 18
Adapting Explainable Machine Learning to Study Mechanical Properties of 2D Hybrid Halide Perovskites
Yao, Y., Han, D., Spooner, K. B., Jia, X., Ebert, H., Scanlon, D. O., & Oberhofer, H. (2024) · Advanced Functional Materials · doi:10.1002/adfm.202411652 · Cited by 18
Artificial intelligence applications in solar energy
Le, T. T., Le, T. T., Le, H. C., Dong, V. H., Paramasivam, P., & Chung, N. (2024) · JOIV International Journal on Informatics Visualization · doi:10.62527/joiv.8.2.2686 · Cited by 20
Ismail, Z., Alali, A. S., Muhammad, A. A. A., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3550658 · Cited by 14
“Alternatively, machine learning (ML) and deep learning (DL) algorithms [4], [5] can be used to optimize photo-voltaic devices like PSCs.”
Zhuang, Z., & Barnard, A. S. (2024) · Computational Materials Science · doi:10.1016/j.commatsci.2024.113344 · Cited by 14
Bayesian parameter estimation for characterising mobile ion vacancies in perovskite solar cells
McCallum, S. G., Nicholls, O., Jensen, K. O., et al. (2023) · Journal of Physics Energy · doi:10.1088/2515-7655/ad0a38 · Cited by 14
Machine learning-based screening of two-dimensional perovskite organic spacers
Mai, Y., Tang, J., Meng, H., Li, X., Liu, M., Zeng, C., Zhang, P., & Li, S. (2024) · Advanced Composites and Hybrid Materials · doi:10.1007/s42114-024-00910-w · Cited by 15
“In addition, the performance testing of PSC also requires a long experimental acquisition time [31].”
Zhu, Z., Zhu, C., Tu, Y., Shao, T., Wang, Y., Liu, W., Liu, Y., Zang, Y., Wei, Q., & Yan, W. (2024) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2024.102316 · Cited by 12
Self-citationDigital manufacturing of perovskite materials and solar cells
Wang, Z., Chen, Z., Wang, B., Wu, C. Z., Zhou, C., Yang, P., Zhang, X., Ni, Z., Chung, C.-Y., Chan, C.-C., et al. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.124120 · Cited by 15
Geometric data analysis-based machine learning for two-dimensional perovskite design
Hu, C.-S., Mayengbam, R., Wu, M.-C., Xia, K., & Sum, T. C. (2024) · Communications Materials · doi:10.1038/s43246-024-00545-w · Cited by 12
Accelerated discovery of perovskite materials guided by machine learning techniques
Kumar, S., Dutta, S., Jaafreh, R., Singh, N., Sharan, A., Hamad, K., & Yoon, D. H. (2023) · Materials Letters · doi:10.1016/j.matlet.2023.135311 · Cited by 11
Unlocking a self-driving research workflow for perovskite photovoltaics
Xie, L., Zhang, Y., Peterkes, N., Li, X., Guo, Y., & Zhou, Y. (2025) · Matter · doi:10.1016/j.matt.2025.102097 · Cited by 14
Machine‐Learning Accelerating the Development of Perovskite Photovoltaics
Liu, T., Wang, S., Shi, Y., Wu, L., Zhu, R., Wang, Y., Zhou, J., & Choy, W. C. H. (2023) · Solar RRL · doi:10.1002/solr.202300650 · Cited by 14
Ge, J., Li, F., Zhang, L., You, J., Liu, S. F., & Jen, A. K. ‐. (2025) · Matter · doi:10.1016/j.matt.2025.102144 · Cited by 13
Wu, B., Zhang, X., Wang, Z., Chen, Z., Liu, S., Liu, J., Xu, Z., Sun, Q., & Zhao, H. (2024) · Journal of Materials Informatics · doi:10.20517/jmi.2024.10 · Cited by 11
Accelerated Multi‐Property Screening of Lead‐Free Halide Double Perovskite via Transfer Learning
Wei, Y., He, J., Yang, C., Yu, W., Feng, J., Liu, X., & Chong, X. (2025) · Advanced Functional Materials · doi:10.1002/adfm.202514377 · Cited by 15
El‐Shishtawy, R. M., & ElShishtawy, N. (2024) · Current Opinion in Colloid & Interface Science · doi:10.1016/j.cocis.2024.101848 · Cited by 11
Machine Learning for Perovskite Solar Cells: An Open‐Source Pipeline
Roberts, N., Jones, D., Schuy, A. J., et al. (2024) · Advanced Physics Research · doi:10.1002/apxr.202400060 · Cited by 11
Liotier, J., Riquelme, A. J., Mwalukuku, V. M., Huaulmé, Q., Kervella, Y., Demadrille, R., & Aumaître, C. (2025) · Materials Horizons · doi:10.1039/d4mh01375a · Cited by 10
All-Season Dual-Mode Thermolator Based on Radiative Cooling and Solar Heating Technology
wang, Y., Tan, X., Yang, X., et al. (2024) · ACS Applied Polymer Materials · doi:10.1021/acsapm.4c02639 · Cited by 10
Self-citationNiu, X., Zhang, Q., Dang, Y., Hu, W., & Sun, Y. (2024) · Journal of the American Chemical Society · doi:10.1021/jacs.4c08132 · Cited by 11
Saha, S., Reddy, M. C. K., Nikhil, T. S., et al. (2023) · Chip · doi:10.1016/j.chip.2023.100075 · Cited by 10
Ayyaz, A., Kaleem, M., Shakoor, A., et al. (2025) · Chemical Physics Letters · doi:10.1016/j.cplett.2025.142433 · Cited by 10
Ionotronics‐Enabled Emerging Halide Perovskite Optoelectronic Devices
Gao, R., Zhu, X., Meng, X., Liu, X., Guo, S., Yao, Q., Chai, G., Miao, J., Tan, H., & Li, R. (2025) · Advanced Materials · doi:10.1002/adma.202519199 · Cited by 10
Liu, J., Xiong, P., Li, C., Hao, H., & Liu, H. (2025) · ACS Sustainable Chemistry & Engineering · doi:10.1021/acssuschemeng.4c10430 · Cited by 10
Zhuang, Z., & Barnard, A. S. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01343 · Cited by 9
Predicting photovoltaic parameters of perovskite solar cells using machine learning
Zhan, H., Wang, M., Chen, J., Yin, X., Yue, Y., & Lu, J. (2024) · Journal of Physics Condensed Matter · doi:10.1088/1361-648x/ad512d · Cited by 9
“To address these challenges and improve the accuracy and efficiency of performance prediction, machine learning (ML) techniques have emerged as a promising research avenue [10– 12].”
Velpandian, M., & Basu, S. (2025) · Indian Chemical Engineer · doi:10.1080/00194506.2024.2444394 · Cited by 9
“Predicting power conversion efficiency of photovoltaic materials [52,53] Gaussian Processes (GP) Probabilistic models that capture complex relationships and uncertainties in data, particularly useful with limited data.”
Robust Perovskite Solar Cells for Extreme and Emerging Applications
Wang, H., Liu, Y., Xiao, Y., et al. (2025) · Advanced Functional Materials · doi:10.1002/adfm.202523571 · Cited by 8
Self-citationAbdellah, I. M., & El‐Shafei, A. (2024) · New Journal of Chemistry · doi:10.1039/d4nj03777d · Cited by 8
Zhu, Y., Gao, F., Niu, Y., et al. (2025) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2025.140926 · Cited by 8
VO2-based dynamic infrared modulation: properties and applications
Xiao, T., Zeng, Z., Ji, H., Liu, B., Long, P., & Jin, S. (2026) · Applied Thermal Engineering · doi:10.1016/j.applthermaleng.2026.129801 · Cited by 8
A UV-resistant porous composite film for radiative cooling and enhanced hydrophobicity
Sun, W., Tan, X., Qi, G., et al. (2024) · Materials Today Communications · doi:10.1016/j.mtcomm.2024.110797 · Cited by 7
Self-citationZhang, Y., Xia, Y., Shakiba, A., Zhang, H., Hao, X., Kumar, P. V., & Suryawanshi, M. P. (2026) · Advanced Science · doi:10.1002/advs.74952 · Cited by 8
“Liu et al. [ 209 ] also highlighted that the model selection is one of the five main parts of a complete ML-driven perovskite research, along with data curation, feature engineering, model validation, and interpretability.”
Lee, J., Noh, J., Lee, H., Lee, Y., Im, J., & Seo, J. (2026) · InfoMat · doi:10.1002/inf2.70124 · Cited by 8
Perovskite solar cells towards industrialization: overcoming challenges with data-driven strategies
Pan, Q., Zhong, Q., Pu, J., Yu, G., Chen, J., Cao, M., & Feng, B. (2026) · Nanoscale · doi:10.1039/d5nr05360a · Cited by 12
Ansari, Z. A., Soni, S., Fatima, S., Siddiqui, S., & Prasad, P. V. H. (2025) · Scientific Reports · doi:10.1038/s41598-025-25848-x · Cited by 7
“…with pinholes, where models utilized 452 training, 12 validation, and 12 test images per class (totalling 2,380 images at 224 224 pixels), reflecting a significant effort given the labour-intensive nature of sample synthesis, preparation, microscopy operation, and expert labelling 16,18,18 .”
Mechanical stability in flexible perovskite solar cells: Interface engineering and device design
Hou, H., Zeng, X., Tang, J., et al. (2026) · FlexMat. · doi:10.1002/flm2.70070 · Cited by 6
Li, X., Ren, L., Zheng, X., Poudel, B., Wang, K., & Qian, J. (2025) · Aggregate · doi:10.1002/agt2.70170 · Cited by 7
Nowsherwan, G. A., Riaz, S., & Naseem, S. (2025) · Multiscale and Multidisciplinary Modeling Experiments and Design · doi:10.1007/s41939-025-00866-4 · Cited by 6
Data-guided design of double-atom catalysts for enhanced electrocatalytic performance
Wei, C., Mu, W., Zhang, H., Liu, Z., & Mu, T. (2025) · Journal of Materials Chemistry A · doi:10.1039/d5ta03021h · Cited by 7
Self-supervised generative models for crystal structures
Liu, F., Chen, Z., Liu, T., Song, R., Lin, Y., Turner, J. J., & Jia, C. (2024) · iScience · doi:10.1016/j.isci.2024.110672 · Cited by 9
“Recent advancements have demonstrated the efficacy of machine learning techniques in predicting various materials properties, including electronic topology, thermodynamic properties, mechanical moduli, etc. [1–9].”
Mohanty, D., & Palai, A. K. (2023) · Advanced Theory and Simulations · doi:10.1002/adts.202300309 · Cited by 6
Inorganic Charge Transport Layers for High‐Performance p‐i‐n Perovskite Solar Cells
Liu, X., Gong, J., Xue, B., Bu, T., Cheng, Y., & Huang, F. (2025) · ChemSusChem · doi:10.1002/cssc.202501739 · Cited by 6
Machine Learning‐Driven Perovskite Research from Experimental Exploration to Industrial Development
Feng, Z., Zhu, X., Hao, M., Yang, A., Tang, J., Zhong, C., Hu, K., Liu, J., Zhang, J., & Lin, X. (2025) · Solar RRL · doi:10.1002/solr.202500464 · Cited by 8
“…commonly evaluated metrics for classification problems are confusion matrix, accuracy, precision, recall, and F 1 -Score, etc., while those commonly used for regression problems are mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), and R-squared ( R 2 ) [65, 80].”
Tian, R., Calderon, A. D., Fang, Q., & Liu, X. (2025) · Materials · doi:10.3390/ma18184429 · Cited by 5
“To overcome these limitations, machine learning (ML) has emerged as a powerful tool to accelerate the development of high-efficiency PSCs [8,9].”
Chen, C., Zhao, H., Xu, Y., Wang, Z., Tuo, Y., Du, Y., Yun, X., Shi, S., Xie, J., Gao, S., et al. (2025) · Solar Energy Materials and Solar Cells · doi:10.1016/j.solmat.2025.113674 · Cited by 6
Wang, J., Lou, Q., Xu, Z., Jin, Y., Luo, G., & Zhou, H. (2025) · Materials Today Electronics · doi:10.1016/j.mtelec.2025.100143 · Cited by 8
Li, H., Zang, Y., Zhu, Z., Zhu, C., Liu, W., Zhang, Z., & Yan, W. (2026) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.6c00119 · Cited by 6
Self-citation
Metadata
- Authors
- Liu, Y., Tan, X., Liang, J., Han, H., Xiang, P., & Yan, W.
- Affiliations
- China Three Gorges University (CN)
- Wuhan National Laboratory for Optoelectronics (CN)
- Corresponding author
- Tan, Xinyu
- Xiang, Peng
- Yan, Wensheng
- Venue
- Advanced Functional Materials
- Publisher
- Wiley
- Published
- 2023-02-15
- Volume
- 33
- Issue
- 17
- ISSN
- 1616-301X (ISSN-L)
- 1616-3028
- OpenAlex
- W4320919502
- Cited by
- 174
- References
- 273
- Citations by year
- 2026: 45 · 2025: 62 · 2024: 49 · 2023: 18
- FWCI
- 12.80
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Advanced Functional Materials (publishedVersion)
- Funders
- National Key Research and Development Program of China (2022YFB4200904)
- National Natural Science Foundation of China (U1765105, 52007104)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Perovskite Materials and Applications
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
- Keywords
- perovskite solar cells, machine learning, materials screening, electrodes, physicochemical property prediction, data-driven materials design, device design
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
