Thermodynamic Stability Landscape of Halide Double Perovskites via High‐Throughput Computing and Machine Learning
The DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.
Abstract
Formability and stability issues are of core importance and difficulty in current research and applications of perovskites. Nevertheless, over the past century, determination of the formability and stability of perovskites has relied on semiempirical models derived from physics intuition, such as the commonly used Goldschmidt tolerance factor, t. Here, through high‐throughput density functional theory (DFT) calculations, a database containing the decomposition energies, considered to be closely related to the thermodynamic stability of 354 halide perovskite candidates, is established. To map the underlying relationship between the structure and chemistry features and the decomposition energies, a well‐functioned machine learning (ML) model is trained over this theory‐based database and further validated by experimental observations of perovskite formability (F1 score, 95.9%) of 246 A 2 B(I)B(III)X 6 compounds that are not present in the training database; the model performs a lot better than empirical descriptors such as tolerance factor t (F1 score, 77.5%). This work demonstrates that the experimental engineering of stable perovskites by ML could solely rely on training data derived from high‐throughput DFT computing, which is much more economical and efficient than experimental attempts at materials synthesis.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Generalized Gradient Approximation Made Simple
Perdew, J. P., Burke, K., & Ernzerhof, M. (1996) · Physical Review Letters · doi:10.1103/physrevlett.77.3865 · Cited by 215,824
From ultrasoft pseudopotentials to the projector augmented-wave method
Kresse, G., & Joubert, D. (1999) · Physical Review B · doi:10.1103/physrevb.59.1758 · Cited by 85,307
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
Organometal Halide Perovskites as Visible-Light Sensitizers for Photovoltaic Cells
Kojima, A., Teshima, K., Shirai, Y., & Miyasaka, T. (2009) · Journal of the American Chemical Society · doi:10.1021/ja809598r · Cited by 23,090
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
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
Efficient Hybrid Solar Cells Based on Meso-Superstructured Organometal Halide Perovskites
Lee, M. M., Teuscher, J., Miyasaka, T., Murakami, T. N., & Snaith, H. J. (2012) · Science · doi:10.1126/science.1228604 · Cited by 10,687
Sequential deposition as a route to high-performance perovskite-sensitized solar cells
Burschka, J., Pellet, N., Moon, S.-J., Humphry-Baker, R., Gao, P., Nazeeruddin, M. K., & Grätzel, M. (2013) · Nature · doi:10.1038/nature12340 · Cited by 9,547
(2012) · Cited by 9,062
Research works printed but not linked: 4
- C. J.Bartel C.Sutton B. R.Goldsmith R. H.Ouyang C. B.Musgrave L. M.Ghiringhelli M.Scheffler arXiv:1801.07700. · arXiv
- 10.1021/jacs.7b07223 · DOI · Paper page
- J.‐P.Correa‐Baena Y.Luo T. M.Brenner J.Snaider S.Sun X.Li M. A.Jensen L.Nienhaus S.Weighold J. R.Poindexter S.Wang Y. S.Meng T.Wang B.Lai M. G.Bawendi L.Huang D. P.Fenning T.Buonassisi arXiv:1804.08722. · arXiv
- Pedregosa F., 2011, J. Mach. Learn. Res., 12, 2825
Cited by
Items 201–235 of 235
Exploration of Double Perovskite Material Space via Machine Learning for Tandem Solar Cells
Wang, Z., Xiong, Z. H., Hu, W. J., Jiang, J., Cheng, Z., Xue, Y. M., Peng, L., & Lin, J. (2025) · Acta Physica Polonica A · doi:10.12693/aphyspola.147.488 · Cited by 2
Review: machine learning-driven design and discovery of halide perovskite materials
Mustapha, N., & Hjiri, M. (2025) · Journal of Materials Science · doi:10.1007/s10853-025-11645-4 · Cited by 1
Talanov, M. V., & Trotsenko, E. G. (2026) · Materials Horizons · doi:10.1039/d5mh02064f · Cited by 2
Ullah, A., Rehman, F., Khan, J., Nasir, M., Ullah, M. F., Bashatah, J. A., Rakhmonov, F., & Ijaz, M. (2026) · Polyhedron · doi:10.1016/j.poly.2026.118278 · Cited by 1
Progress of controllable synthesis of rare-earth containing perovskite nano-materials
Zeng, Z., Du, Y., & Zhang, H. (2020) · Scientia Sinica Chimica · doi:10.1360/ssc-2020-0137 · Cited by 1
Defect suppression of a perovskite film with In2O3 quantum dots for improved solar cell performance
Zhou, D., Yang, G., Li, J., & Pan, J. (2023) · Applied Physics Express · doi:10.35848/1882-0786/acb893 · Cited by 1
Compositional design of compounds with elements not in training data using supervised learning
He, J., Yin, R., Wang, C., Liu, C., Xue, D., Su, Y., Qiao, L. J., Lookman, T., & Bai, Y. (2024) · Journal of Materiomics · doi:10.1016/j.jmat.2024.06.008 · Cited by 1
Harnessing Nano & AI for Sustainable Energy Application
Das, R., & Paria, A. (2025) · Information systems engineering and management · doi:10.1007/978-3-031-77296-2_2 · Cited by 1
From Skeptic to Believer: The Power of ModelsPreprint
Cencer, M. M., Suslick, B. A., & Moore, J. S. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4174304 · Cited by 1
Photovoltaics literature survey (No. 151)
Hameiri, Z. (2019) · Progress in Photovoltaics Research and Applications · doi:10.1002/pip.3154
Computational Modeling and the Design of Perovskite Solar Cells
Yin, W., Gu, H., & Gong, X.-G. (2020) · Springer eBooks · doi:10.1007/978-3-319-44680-6_74 · Cited by 2
Self-citationYang, J., Fan, J., & Li, S. (2022) · Chemistry of Materials · doi:10.1021/acs.chemmater.2c03276
Geometric and topological AI for molecular sciences
Wee, J. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/165903
Fang, C., Wang, H., & Shi, S. (2023) · Acta Physica Sinica · doi:10.7498/aps.72.20230947
Strategies to fabricate full spectrum responsive photocatalysts
Zhu, Q., & Wang, C. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13631-3.00005-7
Neural Networks for Structure-Informed Prediction of Formation Energy (employed in SIPFENN)
Krajewski, A. M., Siegel, J. W., Xu, J., & Liu, Z. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4006802 · Cited by 2
Krajewski, A. M., Siegel, J. W., Shang, S., Wang, Y., Xu, J., & Liu, Z. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4279639 · Cited by 2
Predictive Modeling for Bandgap Tuning in Perovskite Solar Cells Using Machine Learning
Chatterjee, D., Panja, S., Das, S., Kundu, S., Pal, S., & Majumder, K. (2024) · IEEE International Conference of Electron Devices Society Kolkata Chapter (EDKCON) · doi:10.1109/edkcon62339.2024.10870645
Machine learning for predicting and improving perovskite properties
Liu, X., & Zhan, H. (2025) · Semiconductors and semimetals · doi:10.1016/bs.semsem.2025.09.004
Wang, S., Zhao, W., Zhou, M., Liu, T., Wang, Y., Shi, R., Wang, Y., & Zhang, Z. (2025) · Progress in Photovoltaics Research and Applications · doi:10.1002/pip.70060 · Cited by 1
“In terms of materials design, combining material stability predictors with essential factors enables researchers to design novel materials more effectively [78, 79].”
Liang, G., & Zhang, J. (2026) · Materials · doi:10.3390/ma19102018 · Cited by 1
“Traditionally, E g and ∆ H f are usually obtained from calculations based on DFT in a traditional way, which is computationally expensive and time-consuming [11,12], making it impossible to apply to a large database.”
Cheng, G., Zhou, K., Gong, X.-G., & Yin, W. (2026) · AI for Science · doi:10.1088/3050-287x/ae70c4
“These materials databases provide extensive reference data that form the foundation for data-driven materials research, and have greatly accelerated the development of ML methodologies in the field [13, 34].”
Self-citationSaid, M., Chabri, I., El-allaly, E.-D., & Oubelkacem, A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115781
Akinpelu, S. B., Abolade, S. A., Okafor, E., Obada, D. O., Kumar, S. R., Ukpong, A. M., Healy, J., & Akande, A. (2026) · Materials Today Communications · doi:10.1016/j.mtcomm.2026.115628
Lande, D., Ugemuge, N. S., Dhale, S. P., Pusdekar, A., & Muley, A. (2026) · Canadian Metallurgical Quarterly · doi:10.1080/00084433.2026.2689872
Maqsood, S., Noor, N. A., Mumtaz, S., Mahmood, A., & Alomayrah, N. (2026) · ChemistrySelect · doi:10.1002/slct.202506027
Density Functional Theory (DFT) for Energy Conversion Systems
Asogwa, V. C., Asogwa, L. I., & Ezema, F. I. (2026) · Springer eBooks · doi:10.1007/978-3-031-93307-3_9
Fatima, Q., Haidry, A. A., Ahmad, U., & Zhang, H. (2026) · Advanced Theory and Simulations · doi:10.1002/adts.70513 · Cited by 1
Peng, J. J., Duan, M., Li, M., He, Y., Hao, H., Li, M., Zhang, C., Chen, Z., Yu, Q., Yan, Q., et al. (2026) · Journal of Materials Chemistry A · doi:10.1039/d6ta04986a · Cited by 1
Machine learning enabled discovery of photocatalytic ABX 3 perovskite materials
Akinpelu, S. B., Abolade, S. A., Okafor, E., Obada, D. O., Syam Kumar, R., Ukpong, A. M., Healy, J., & Akande, A. (2026) · Digital Discovery · doi:10.1039/d6dd00010j
Wang, B., & Wang, J. (2026) · Molecules · doi:10.3390/molecules31183175 · Cited by 1
“Formation energy is a critical indicator for evaluating the synthetic feasibility, structural stability, and application potential of LFDPs [17].”
A FAIR approach towards constructing a computational perovskite database
Desai, R., Strachan, A. H., & Mannodi‐Kanakkithodi, A. (2026) · MRS Communications · doi:10.1557/s43579-026-01039-1
P, J. J. G. (2026) · Discover Chemistry. · doi:10.1007/s44371-026-00985-y · Cited by 1
“Li et al. [31] illustrate the scale such campaigns can reach in the perovskite space: they combined a DFT-calculated thermodynamic stability database for halide double perovskites with a machine learned, physically interpretable stability classifier, validated the classifier against several hundred…”
Wei, Q., Zhang, H., Peng, C., Tian, Y., Zhang, Y., Yang, Y., Liu, M., & Xu, N. (2026) · Nanomaterials · doi:10.3390/nano16191217
“Its narrower contribution is a validation architecture that combines formula-level leakage control, explicit chemical-distribution-shift tests, descriptor-availability analysis, and prediction-level uncertainty in one reproducible benchmark [16,18–20].”
Jamal, M. W., Ali, R., Raza, A., Rabhi, S., & Bouderbala, I. Y. (2026) · physica status solidi (b) · doi:10.1002/pssb.70340
Metadata
- Authors
- Li, Z., Xu, Q., Sun, Q., Hou, Z., & Yin, W.
- Affiliations
- Soochow University (CN)
- National Institute for Materials Science (JP)
- Corresponding author
- Yin, Wan‐Jian
- Venue
- Advanced Functional Materials
- Publisher
- Wiley
- Published
- 2019-01-17
- Volume
- 29
- Issue
- 9
- ISSN
- 1616-301X (ISSN-L)
- 1616-3028
- OpenAlex
- W2909184124
- Cited by
- 233
- References
- 61
- Citations by year
- 2026: 22 · 2025: 29 · 2024: 40 · 2023: 32 · 2022: 35 · 2021: 34 · 2020: 28 · 2019: 13
- FWCI
- 10.11
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Advanced Functional Materials (publishedVersion)
- Funders
- National Natural Science Foundation of China (11674237, 51602211)
- Natural Science Foundation of Jiangsu Province (BK20160299)
- 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
- halide double perovskites, thermodynamic stability, decomposition energy, high-throughput density functional theory, machine learning prediction, structure-property relationships, tolerance factor, materials 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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.