Interpretable and Explainable Machine Learning for Materials Science and Chemistry
Open accessThe DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Abstract
High Resolution Image Download MS PowerPoint Slide Conspectus Machine learning has become a common and powerful tool in materials research. As more data become available, with the use of high-performance computing and high-throughput experimentation, machine learning has proven potential to accelerate scientific research and technology development. Though the uptake of data-driven approaches for materials science is at an exciting, early stage, to realize the true potential of machine learning models for successful scientific discovery, they must have qualities beyond purely predictive power. The predictions and inner workings of models should provide a certain degree of explainability by human experts, permitting the identification of potential model issues or limitations, building trust in model predictions, and unveiling unexpected correlations that may lead to scientific insights. In this work, we summarize applications of interpretability and explainability techniques for materials science and chemistry and discuss how these techniques can improve the outcome of scientific studies. We start by defining the fundamental concepts of interpretability and explainability in machine learning and making them less abstract by providing examples in the field. We show how interpretability in scientific machine learning has additional constraints compared to general applications. Building upon formal definitions in machine learning, we formulate the basic trade-offs among the explainability, completeness, and scientific validity of model explanations in scientific problems. In the context of these trade-offs, we discuss how interpretable models can be constructed, what insights they provide, and what drawbacks they have. We present numerous examples of the application of interpretable machine learning in a variety of experimental and simulation studies, encompassing first-principles calculations, physicochemical characterization, materials development, and integration into complex systems. We discuss the varied impacts and uses of interpretabiltiy in these cases according to the nature and constraints of the scientific study of interest. We discuss various challenges for interpretable machine learning in materials science and, more broadly, in scientific settings. In particular, we emphasize the risks of inferring causation or reaching generalization by purely interpreting machine learning models and the need for uncertainty estimates for model explanations. Finally, we showcase a number of exciting developments in other fields that could benefit interpretability in material science problems. Adding interpretability to a machine learning model often requires no more technical know-how than building the model itself. By providing concrete examples of studies (many with associated open source code and data), we hope that this Account will encourage all practitioners of machine learning in materials science to look deeper into their models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · Proceedings of IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.1993.341010 · Cited by 14,265
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
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
Proceedings of IEEE International Conference on Computer Vision
(1995) · Proceedings of IEEE International Conference on Computer Vision · doi:10.1109/iccv.1995.466933 · Cited by 12,860
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Explanation in Artificial Intelligence: Insights from the Social Sciences
Miller, T. (2017) · arXiv · doi:10.48550/arxiv.1706.07269 · Cited by 5,338
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
The Book of Why: The New Science of Cause and Effect
Pearl, J., & Mackenzie, D. N. (2018) · Cited by 3,870
Explaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507
Goldstein, A., Kapelner, A., Bleich, J., & Pitkin, E. (2015) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2014.907095 · Cited by 1,861
Research works printed but not linked: 14
- Biran O., 2017, Workshop on Explainable AI (XAI), 8, 8
- Mitchell T. M., 1997, Machine Learning
- 10.1088/1361-648X/abea1c/meta · doi:10.1088/1361-648x/abea1c/meta
- Balduzzi D., 2017, International Conference on Machine Learning, 342
- 10.48550/arXiv.1711.06104 · DOI
- J. Pearl, arXiv preprint arXiv:1801.04016 (2018). · arXiv
- S. V. Kalinin, A. Ghosh, R. Vasudevan, and M. Ziatdinov, arXiv preprint arXiv:2109.07350 (2021). · arXiv
- 10.48550/arXiv.2109.07350 · arXiv · doi:10.48550/arxiv.2109.07350
- Medical Image Learning with Less Labels and Imperfect Data (Springer, 2019) pp. 37-44.
- I. Higgins, L. Matthey, A. Pal, C. Burgess, X. Glorot, M. Botvinick, S. Mohamed, and A. Lerchner, (2016).
- X. Li, Y. Zhou, N. C. Dvornek, Y. Gu, P. Ventola, and J. S. Duncan, in International Conference on Medical Image Computing and Computer-Assisted Intervention (Springer, 2020) pp. 792-801.
- C. Frye, I. Feige, and C. Rowat, arXiv preprint arXiv:1910.06358 (2019). · DOI
- O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al. , International journal of computer vision 115 , 211 (2015).
- Leamer E. E., 1983, American Economic Review, 73, 31
Cited by
Items 101–200 of 435
Jaffal, E. I., Lee, S., Shiryaev, D., Vtorov, A., Barua, N. K., Kleinke, H., & Oliynyk, A. O. (2025) · Digital Discovery · doi:10.1039/d4dd00332b · Cited by 16
Hu, H., Wang, B., Zhang, D., Yan, K., Tan, T., & Wu, D. (2025) · Journal of Materials Chemistry C · doi:10.1039/d5tc00865d · Cited by 14
Zhang, J., Jia, X., Li, H., Xiao, F., Wang, Q., & Zhao, N. (2025) · ACS Sustainable Chemistry & Engineering · doi:10.1021/acssuschemeng.5c02957 · Cited by 12
Qureshi, N., Bang, J., & Doh, J. (2025) · Nanotechnology Reviews · doi:10.1515/ntrev-2025-0200 · Cited by 14
Gee, W., Doyle, A. G., Vargas, S., & Alexandrova, A. N. (2025) · Digital Discovery · doi:10.1039/d5dd00220f · Cited by 19
Rahman, A., Ali, M. H., Mahmood, M. A., & Liou, F. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16782-3 · Cited by 15
Bridger, A., David, W. I. F., Wood, T. J., Danaie, M., & Butler, K. T. (2023) · npj Computational Materials · doi:10.1038/s41524-022-00960-y · Cited by 20
“VAEs have recently shown great promise for processing and understanding large scienti fi c datasets, extracting useful representations of data 23 – 25 .”
MethodSelf-citationLamprou, V., Kallipolitis, A., & Maglogiannis, I. G. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108238 · Cited by 21
Li, S., Mao, X., Cao, X.-Q., Feng, Y., Zhang, Y., & Yin, H. (2025) · Colloids and Surfaces A Physicochemical and Engineering Aspects · doi:10.1016/j.colsurfa.2025.136400 · Cited by 13
Jing, Y., Zhang, C., Mine, S., Zhang, X., He, C., Zhang, N., Guo, X. M., Anzai, A., Oka, K., Toyoshima, R., et al. (2025) · ACS Catalysis · doi:10.1021/acscatal.5c06074 · Cited by 15
Machine learning in tribology: A review on framework, case studies, and future perspectives
Yadong, L. I., Liu, B., Chang, Z., Zhang, Z., Ouyang, W., Liu, Z., Jiang, Q., Liu, Y., Huang, A. W., Wu, Y., et al. (2026) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2026.01.029 · Cited by 16
He, M., Wang, Y., & Fan, Y. (2024) · Journal of Physics Condensed Matter · doi:10.1088/1361-648x/ad4aab · Cited by 11
“Most ML approaches focus on average properties or lack interpretability, missing out on local details [120, 121].”
BackgroundFoong, L. K., Blažek, V., Prokop, L., Mišák, S., Atamurotov, F., & Khalilpoor, N. (2024) · Engineering Applications of Computational Fluid Mechanics · doi:10.1080/19942060.2024.2391988 · Cited by 14
“Moreover, there can be restrictions on how interpretable neural network models can be, which makes it challenging to understand the underlying principles driving predictions and obtain useful insights (Oviedo et al., 2022).”
Wei, F., Ge, B., Dong, P., Wan, Q., Hu, X., & Lin, S. (2024) · Science China Materials · doi:10.1007/s40843-023-2771-4 · Cited by 11
“Among them, interpretable ML can provide insight into the correlation between the obtained features and the target attributes, thus accelerating the development of new catalysts [43,57].”
Depth analysis of battery performance based on a data-driven approach
Zhang, Z., Sun, H., & Sun, H. (2023) · Electrochimica Acta · doi:10.1016/j.electacta.2023.143565 · Cited by 10
Learning from machine learning: the case of band-gap directness in semiconductors
Ogoshi, E., Neto, M. P., Acosta, C. M., Nascimento, G. M., Rodrigues, J. N. B., Oliveira, O. N., Paulovich, F. V., & Dalpian, G. M. (2024) · Discover Materials · doi:10.1007/s43939-024-00073-x · Cited by 14
“Recent works [6, 41], however, indicate that Machine Learning can be used in more complex tasks, including interpretation of physical phenomena.”
Vubangsi, M., Mubarak, A. S., & Al-Turjman, F. M. (2024) · Energy Reports · doi:10.1016/j.egyr.2024.03.035 · Cited by 15
Active causal learning for decoding chemical complexities with targeted interventions
Fox, Z., & Ghosh, A. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad6feb · Cited by 15
Toward accelerated discovery of solid catalysts using extrapolative machine learning approach
Toyao, T. (2024) · Chemistry Letters · doi:10.1093/chemle/upae163 · Cited by 10
Lee, S. P., Lee, S. H., & Sohn, I. (2025) · Journal of Material Science and Technology · doi:10.1016/j.jmst.2025.06.012 · Cited by 10
Yang, P., Henle, E. A., Fern, X. Z., & Simon, C. M. (2022) · The Journal of Chemical Physics · doi:10.1063/5.0090573 · Cited by 10
Design of New Ternary Nitrides for Photovoltaic Applications via High-Throughput Calculations
Xue, P., Chu, D., Xie, C., Tikhonov, E., & Butler, K. T. (2022) · The Journal of Physical Chemistry C · doi:10.1021/acs.jpcc.2c05458 · Cited by 9
Self-citationExplainable artificial intelligence for machine learning prediction of bandgap energies
Masuda, T., & Tanabe, K. (2024) · Journal of Applied Physics · doi:10.1063/5.0226151 · Cited by 12
Mim, J. J., Rakib, S., Akter, S., Nisha, J. R., Khan, S., Rahman, S., Manik, M. H., & Hossain, N. (2025) · Journal of Nanoparticle Research · doi:10.1007/s11051-025-06472-2 · Cited by 14
From prediction to understanding: A review of XAI applications and innovations in materials science
Cravero, F., Ponzoni, I., Díaz, M. F., & Vázquez, G. E. (2026) · Computational Materials Science · doi:10.1016/j.commatsci.2026.114493 · Cited by 14
Elagamy, S. H., Chanduluru, H. K., Obaydo, R. H., & LOTFY, H. M. (2026) · International Journal of Analytical Chemistry · doi:10.1155/ianc/2645726 · Cited by 11
Hatanaka, M., Kato, H., Sakai, M., Kariya, K., Nakatani, S., Yoshimura, T., & Inagaki, T. (2023) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.3c02179 · Cited by 10
Wang, Y., Kazemi, A., Jing, T., Ding, Z., Li, L., & Yang, S. (2024) · Extreme Mechanics Letters · doi:10.1016/j.eml.2024.102172 · Cited by 9
Wang, F., Liu, W., Sun, Y., Zhang, B., Li, H., Chen, L., Hou, B., & Zhang, H. (2024) · Corrosion Reviews · doi:10.1515/corrrev-2023-0162 · Cited by 8
Abdolahi, J., Robe, D., Larson, R. G., Kirley, M., & Hajizadeh, E. (2025) · Journal of Rheology · doi:10.1122/8.0000930 · Cited by 12
Multitarget Generate Electrolyte Additive for Lithium Metal Batteries
Liu, X., Chu, J., Xue, S., Wang, D., Lu, Z., Zhang, M., Liu, Y., Xu, X., Zhang, Y., Long, J., et al. (2025) · Advanced Materials · doi:10.1002/adma.202502086 · Cited by 11
Tomura, S., Wilkinson, M. J., Powell, O. M., & Cooper, M. (2025) · The Plant Genome · doi:10.1002/tpg2.70138 · Cited by 8
“Interpretable prediction models have been leveraged in a wide range of research fields, such as healthcare (Abdullah et al., 2021; Baniecki et al., 2025; Stiglic et al., 2020), chemistry (Oviedo et al., 2022; Tavakoli et al., 2023), and physics (Wet-zel et al., 2025).”
Shorey, R., Esmizadeh, E., & Mekonnen, T. H. (2025) · Progress in Polymer Science · doi:10.1016/j.progpolymsci.2025.102064 · Cited by 14
Advances in graph neural networks for alloy design and properties predictions: a review
Zhao, Z., Hu, T., Bi, S., Guan, D., Xu, S., Chen, C., Xuan, W., & Ren, Z. (2026) · Journal of Materials Informatics · doi:10.20517/jmi.2025.42 · Cited by 12
Yang, W., Xu, Z., Li, J., Zhang, L., Shu, M., Cai, J., Yao, T., Tang, X., Liu, Y., Luo, S., et al. (2026) · Journal of Materials Chemistry A · doi:10.1039/d5ta08221h · Cited by 9
Data-Driven Engineering of Antimicrobial Nanomaterials for Food Safety and Biomedical Systems
Nguyen, H. L., Nguyen, T. B. N., & Nguyen, T. B. N. (2026) · Nanomaterials · doi:10.3390/nano16120764 · Cited by 10
“Such strategies are expected to enhance reliability and accelerate translation of AI-guided nanomaterial design into practical food and biomedical applications [41,42].”
Li, T., Li, J., Kong, Z., Peng, Y., Shen, J., Zhang, L., & Liang, L. (2024) · Desalination · doi:10.1016/j.desal.2024.117737 · Cited by 8
Unifying theory of electronic descriptors of metal surfaces upon perturbation
Huang, Y., Wang, S., Kamanuru, M., Achenie, L. E. K., Kitchin, J. R., & Xin, H. (2024) · Physical review. B./Physical review. B · doi:10.1103/physrevb.110.l121404 · Cited by 9
Heat Transfer in Composite Materials: Mechanisms and ApplicationsPreprint
Alaghemandi, M. (2025) · Qeios · doi:10.32388/efedmt · Cited by 16
The disagreement dilemma in explainable AI: can bias reduction bridge the gap
Bhardwaj, N., & Parashar, G. (2025) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-025-02712-9 · Cited by 8
“Further, applying interpretable and explainable machine learning techniques in materials science and chemistry plays a vital role (Oviedo et al. 2022).”
Examining proton conductivity of metal–organic frameworks by means of machine learning
Dudakov, I. V., Savelev, S. A., Nevolin, I. M., Mitrofanov, A. A., Korolev, V., & Gorbunova, Y. G. (2025) · Physical Chemistry Chemical Physics · doi:10.1039/d5cp00090d · Cited by 8
Raman Peak Features Matching: Enhancing Spectral Analysis through Feature Augmentation
Yin, P., Lian, X., Wu, X., Xiao, Y., Feng, C., Lv, Y., Yi, L., Liang, M., Ge, G., Dmitriy, K., et al. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.4c06679 · Cited by 10
Explainable Graph Neural Networks in Chemistry: Combining Attribution and Uncertainty Quantification
Komissarov, L., Manevski, N., Zbinden, K. G., & Sach-Peltason, L. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01003 · Cited by 12
Mimura, S., Masuda, T., Miyamoto, S., & Tanabe, K. (2025) · Chemical Engineering Journal Advances · doi:10.1016/j.ceja.2025.100929 · Cited by 11
Machine Learning for Neurotransmitter Monitoring by Fast Voltammetry: Current and Future Prospects
Movassaghi, C. S., & Andrews, A. M. (2025) · ACS Chemical Neuroscience · doi:10.1021/acschemneuro.5c00543 · Cited by 9
Gouvêa, R. A., Breuck, P.-P. D., Pretto, T., Rignanese, G., & Santos, M. J. L. (2026) · npj Computational Materials · doi:10.1038/s41524-025-01938-2 · Cited by 18
“Moreover, it aligns with the growing demand for explainable AI 27,28 , which is essential for the advancement of self-driving laboratories in materials discovery and optimization 29 .”
Asif, M., Hakeem, L., Yao, C., Hira, Bibi, R., Bilal, M., & Zeb, H. (2026) · RSC Advances · doi:10.1039/d6ra01011c · Cited by 7
“9 In this study, we explore a proof – of – concept combination of Coats – Redfern kinetic/ thermodynamic analysis with a descriptor-based ML model for sapodilla leaves.”
Wong, K., Qi, R., Yang, Y., Luo, Z., Guldin, S., & Butler, K. T. (2024) · JACS Au · doi:10.1021/jacsau.4c00368 · Cited by 7
Self-citationMiyan, N., Krishnan, N. M. A., & Das, S. (2024) · Journal of Building Engineering · doi:10.1016/j.jobe.2024.111248 · Cited by 15
Machine Learning Application for Functional Properties Prediction in Magnetic Materials
Milyutin, V. A., & Никульченков, Н. Н. (2024) · The Physics of Metals and Metallography · doi:10.1134/s0031918x24601471 · Cited by 8
“It is worth noting that this challenge remains unresolved in full, although recent years have seen active development in methods aimed at enhancing ML interpretability [84].”
Gagliardi, R. V., & Andenna, C. (2025) · Atmosphere · doi:10.3390/atmos16050491 · Cited by 11
Crystal nucleation and growth dynamics of aluminum via quantum-accurate MD simulations
Tipeev, A. O., & Zanotto, E. D. (2025) · Acta Materialia · doi:10.1016/j.actamat.2025.121245 · Cited by 7
ACES-GNN: can graph neural network learn to explain activity cliffs?
Chen, X., Yu, D., Zhao, L., & Liu, F. (2025) · Digital Discovery · doi:10.1039/d5dd00012b · Cited by 13
Song, J., Sun, Q., Skirtach, A. G., & Parakhonskiy, B. V. (2025) · Advances in Colloid and Interface Science · doi:10.1016/j.cis.2025.103732 · Cited by 8
Machine Learning Unlocks New Directions in Halide Perovskite Research
Choe, H., Yoon, H., Kim, I., & Kim, S. Y. (2025) · ChemElectroChem · doi:10.1002/celc.202500282 · Cited by 10
Bobbili, V. S. R., Chandrasekara Sastry, C., & Hafeezur Rahman, A. (2026) · Rapid Prototyping Journal · doi:10.1108/rpj-08-2025-0362 · Cited by 8
Li, Q., Guo, Z., Li, J., Li, X., & Ban, B. (2024) · Applied Sciences · doi:10.3390/app14188264 · Cited by 6
Karampinis, I., Karabini, M. A., Rousakis, T. C., Iliadis, L., & Karabinis, A. I. (2024) · Sensors · doi:10.3390/s24247955 · Cited by 8
“This included the implementation of so-called intrinsically explainable models [19], such as LASSO logistic regression, which also produced analytical expressions.”
Stability of drop-like water cluster
Kirov, M. V. (2024) · Chemical Physics Letters · doi:10.1016/j.cplett.2024.141849 · Cited by 6
Machine Learning-Driven Density Prediction for Nanomaterials
Ansaf, S. (2024) · Wasit Journal of Pure sciences · doi:10.31185/wjps.538 · Cited by 6
Kengkanna, A., & Ohue, M. (2023) · IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb56990.2023.10264879 · Cited by 8
Linear graphlet models for accurate and interpretable cheminformatics
Tynes, M., Taylor, M. G., Janßen, J., Burrill, D. J., Pérez, D., Yang, P. X., & Lubbers, N. (2024) · Digital Discovery · doi:10.1039/d4dd00089g · Cited by 9
“In the ML interpretability literature, intrinsically interpretable models 18,20 are those wherein the model functional form and mechanisms for prediction are transparent and meaningful.”
BackgroundMethodLee, S., Chen, C., Garcia, G., & Oliynyk, A. O. (2023) · ChemRxiv · doi:10.26434/chemrxiv-2023-0nlzl · Cited by 6
Furth, N., Imel, A. E., & Zawodzinski, T. A. (2024) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.4c00936 · Cited by 9
Sun, S., Tian, F., Zhao, C., Xie, M., Li, W., Yu, W., Cui, K., & Li, L. (2025) · The Journal of Chemical Physics · doi:10.1063/5.0281450 · Cited by 5
Krupska-Klimczak, M., Frontczak, M., Świerczyński, Z., Semenov, S., Kajewski, D., & Jankowska‐Sumara, I. (2025) · Materials · doi:10.3390/ma18194444 · Cited by 5
“Moreover, many ML approaches currently function as “black boxes,” providing limited physical interpretability of their predictions, which hinders their acceptance and utility within the materials science community [17].”
SHAP-based ensemble machine learning for predicting hveem-derived shear strength from marshall tests
Arabani, M., Safari, M., & Rahimabadi, M. M. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.109853 · Cited by 6
Explain the World—Using Causality to Facilitate Better Rules for Fuzzy Systems
Zhang, T., Wagner, C., & Garibaldi, J. M. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3457962 · Cited by 7
“Where such identification of causal relationships is successful, and where these AI systems are explainable, the explanations of their underlying models will map to explanations of the real-world processes which they capture [9].”
Sequential Sampling Methods for Finding Classification Boundaries in Engineering Applications
Bhat, M., & Kitchin, J. R. (2023) · Industrial & Engineering Chemistry Research · doi:10.1021/acs.iecr.3c02362 · Cited by 5
Vasylenko, A., Antypov, D., Gusev, V. V., Gaultois, M. W., Dyer, M. S., & Rosseinsky, M. J. (2022) · Research Square · doi:10.21203/rs.3.rs-1334648/v1 · Cited by 5
Explaining structure-activity relationships using locally faithful surrogate modelsPreprint
Gandhi, H. A., & White, A. D. (2022) · ChemRxiv · doi:10.26434/chemrxiv-2022-v5p6m-v2 · Cited by 8
Yan, S., Xu, P., Li, G., Zhu, Y., Wu, Y., Chen, Q., Liu, S., Li, Q., & Tang, M. (2024) · Journal of Materiomics · doi:10.1016/j.jmat.2024.100968 · Cited by 4
Li, Y., Ge, X., & Liu, B. (2024) · Chemical Engineering Research and Design · doi:10.1016/j.cherd.2024.12.015 · Cited by 5
A new ionic radii scale derived from perovskite oxides
Gzyl, A. S., Addo, P. K., & Molero-Sánchez, B. (2025) · Journal of Solid State Chemistry · doi:10.1016/j.jssc.2025.125254 · Cited by 7
Zhang, D., Li, Y., Li, J., Xia, Y., Avid, B., Long, L., Ping, Y., Piao, Y., Xing, Y., & Gui, X. (2025) · Colloids and Surfaces A Physicochemical and Engineering Aspects · doi:10.1016/j.colsurfa.2025.138313 · Cited by 4
Wang, Y., Chen, L., Cheng, L., Wang, E., Sheng, Z., & Zhang, L. (2025) · Materials · doi:10.3390/ma18235460 · Cited by 6
Saleh, G., & Manna, L. (2025) · Journal of the American Chemical Society · doi:10.1021/jacs.5c08790 · Cited by 6
Signori-Iamin, G., Márquez, R., Bastida, G. A., Tarrés, Q., Santos, A. F., & Marc, D.-A. (2026) · Cellulose · doi:10.1007/s10570-025-06921-0 · Cited by 4
“This complexity makes predictive modelling of complex process-structure–property relationships valuable, especially for process control and material design purposes (Oviedo et al. 2022; Santos et al. 2022; Signori-Iamin et al. 2022; Unni et al. 2024).”
Lee, Y., Ahmed, A., Lee, J., Ok, K. M., & You, T. (2026) · Journal of Materials Chemistry A · doi:10.1039/d5ta08713a · Cited by 4
Text mining-assisted machine learning prediction and experimental validation of emission wavelengths
Huang, L., Zhang, X., Li, S., & Xie, R. (2026) · npj Computational Materials · doi:10.1038/s41524-026-01967-5 · Cited by 5
“To construct an inter-pretable prediction model 32 , we fully considered the physical and chemical factors in fl uencing the luminescence of Eu 2 + .”
Chowdhury, P. R., Medhi, H., Bhattacharyya, K. G., & Hussain, C. M. (2026) · Coordination Chemistry Reviews · doi:10.1016/j.ccr.2026.217886 · Cited by 4
AI-ML innovations in membrane technology: current progress and future prospects
Ramkumar, N., Chandran, D. G., & Monash, P. (2026) · Chemical Engineering Journal Advances · doi:10.1016/j.ceja.2026.101408 · Cited by 4
Petrophysical prediction of oil reservoirs using explainable artificial intelligence
Li, S., Wei, Z., Yang, Y., Zhang, J., & Cheng, Y. (2025) · Geophysics · doi:10.1190/geo2024-0271.1 · Cited by 5
Understanding interpretable patterns of Shapley behaviours in materials data
Liu, T., & Barnard, A. S. (2025) · Machine Learning Engineering · doi:10.1088/3049-4761/adaaf6 · Cited by 6
Xiao, L., Liu, H., Liu, X., Zhou, H., Zhang, Y., Liu, B., Wu, J., & Lin, J. H. (2025) · Journal of Colloid and Interface Science · doi:10.1016/j.jcis.2025.137827 · Cited by 5
Sánchez-Palencia, P., Hamad, S., Palacios, P., Grau‐Crespo, R., & Butler, K. T. (2022) · Digital Discovery · doi:10.1039/d2dd00038e · Cited by 4
Self-citationTarget Material Property‐Dependent Cluster Analysis of Inorganic Compounds
Sato, N., Takahashi, A., Kiyohara, S., Terayama, K., Tamura, R., & Oba, F. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202400253 · Cited by 7
Ng, Y. S., & Zheng, J. (2025) · ACS Applied Energy Materials · doi:10.1021/acsaem.5c00469 · Cited by 4
Solubilization of inclusion bodies: insights from explainable machine learning approaches
Walther, C., Martinetz, M. C., Friedrich, A., Tscheließnig, A., Voigtmann, M., Jung, A., Brocard, C., Bluhmki, E., & Smiatek, J. (2023) · Frontiers in Chemical Engineering · doi:10.3389/fceng.2023.1227620 · Cited by 4
DeepDeg: Forecasting and explaining degradation in novel photovoltaicsPreprint
Oviedo, F., Hayden, D. S., Heumeuller, T., Wortmann, J., Perea, J. D., Naik, R. R., Xue, H., Ferres, J. L., Fisher, J. S., Brabec, C. J., et al. (2023) · ChemRxiv · doi:10.26434/chemrxiv-2023-j2pvp · Cited by 4
Self-citationHarnessing the leading edge: machine learning ventures in chemistry and materials science
Li, Y., Guo, F., Lien, S., Yusoff, A. R. B. M., Zheng, Z., Zhang, J., & Gao, P. (2025) · Physical Chemistry Chemical Physics · doi:10.1039/d5cp00373c · Cited by 5
Behera, S. A., Krishna, P. K., & Achary, P. G. R. (2025) · Challenges and advances in computational chemistry and physics · doi:10.1007/978-3-031-78736-2_5 · Cited by 6
Huang, C., Zhang, Y., Li, S., Wang, H., Wang, Y., Wei, S., & Sun, S. (2025) · Chemical Science · doi:10.1039/d5sc00494b · Cited by 5
“53,54 It is worth emphasizing that a novel perspective is introduced here to understand the neural network model.”
Lost Data in Electron Microscopy
Ivanova, N. M., Kashin, A. S., & Ananikov, V. P. (2025) · Chemistry · doi:10.3390/chemistry7050160 · Cited by 7
Empowering scientific discovery with explainable small domain-specific and large language models
Yu, H., Wang, Y., Cheng, T., Yan, Y., Dawson, K. A., Li, S. F. Y., Zheng, Y., & Jin, Y. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11365-w · Cited by 5
“Therefore, researchers in the fields of materials science and chemistry argue that there is no reason to keep the AI model a black box (Oviedo et al. 2022 ).”
Hu, H., Wang, B., Zhang, D., Yan, K., Tan, T., & Wu, D. (2025) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c14694 · Cited by 3
Normalized Descriptor for Unbiased Screening of Second-Order Nonlinear Optical Materials
Nyíri, A., Waters, M. J., & Rondinelli, J. M. (2026) · ACS Photonics · doi:10.1021/acsphotonics.5c02758 · Cited by 3
Artificial intelligence in the discovery and design of molecular semiconductors: a systematic review
Zollner, M., Moshfeghi, Y., & Nematiaram, T. (2026) · Digital Discovery · doi:10.1039/d5dd00552c · Cited by 7
Interpretable surrogate modeling for polymers: A SHAP-guided framework for descriptor-level analysis
Shireen, Z., & Brandl, C. (2026) · Computational Materials Science · doi:10.1016/j.commatsci.2026.114703 · Cited by 4
Elagamy, S. H., & Elattar, R. H. (2026) · Analytical Letters · doi:10.1080/00032719.2026.2709666 · Cited by 4
Metadata
- Authors
- Oviedo, F., Ferres, J. L., Buonassisi, T., & Butler, K. T.
- Affiliations
- Microsoft (United States) (US)
- Massachusetts Institute of Technology (US)
- Rutherford Appleton Laboratory (GB)
- Corresponding author
- Oviedo, Felipe
- Butler, Keith T.
- Venue
- Accounts of Materials Research
- Publisher
- American Chemical Society (ACS)
- Published
- 2022-06-03
- Volume
- 3
- Issue
- 6
- Pages
- 597-607
- ISSN
- 2643-6728 (ISSN-L)
- OpenAlex
- W3208302614
- Cited by
- 435
- References
- 59
- Citations by year
- 2026: 164 · 2025: 121 · 2024: 80 · 2023: 52 · 2022: 18
- FWCI
- 19.05
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Accounts of Materials Research (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
- Science and Technology Facilities Council (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Microsoft
- Singapore-MIT Alliance for Research and Technology Centre
- National Research Foundation
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
- Keywords
- model interpretability, explainable machine learning, materials science, chemistry, model explanation, uncertainty estimation, causal inference, generalization, first-principles calculations, materials discovery, high-throughput experimentation
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.