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 401–435 of 435
Human–AI Jurisdiction Boundaries in Computational and Data-Driven Materials Engineering
Liu, W., & Min, Z. (2025) · Journal of Computational and Data-Driven Materials Engineering · doi:10.68159/k608010423
Discovery Recommendation Systems: Reframing Materials Selection Algorithms
Liu, W., & Min, Z. (2024) · Journal of Computational and Data-Driven Materials Engineering · doi:10.68159/m166580906
Abdelsalam, H., Wang, Z., Alkhamisi, M. M., Abd-Elkader, O. H., Zhang, L., & Zhang, Q. (2026) · Applied Physics A · doi:10.1007/s00339-026-10204-1
SHAP-Interpretable Regression Models for Entropy Prediction in Molecular Quantum Chemistry
Jia, X. (2026) · doi:10.1145/3842702.3842703
“However, despite the good results that have been achieved in many fields, without interpretability, it cannot be applied to science in the event of physical verification [3].”
Millner, G., Wang, T.-W., Shen, S., Li, Y., & Chen, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7447105
Thabet, R. H. (2026) · Research Square · doi:10.21203/rs.3.rs-10878910/v1
Trustworthy AI-Guided Transfer Learning for Cross-Architecture Prediction of Solid Oxide Fuel CellsPreprint
Li, S., Li, J., Yang, Q., Zhou, W., & Yao, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7477809
Koo, M. S., ABOUZEID, R. E., Moon, R. J., Tajvidi, M., Walker, C. C., Korniejenko, K., & Wu, Q. (2026) · ACS Applied Polymer Materials · doi:10.1021/acsapm.6c02898
Puspitasari, A., Duong, T. K. N., Wibowo, A. F., Doan, V. H. M., Vo, T. T., Choi, J., Kim, Y. H., Ahn, J. S., Mondal, S., & Oh, J. (2026) · Biomaterials Advances · doi:10.1016/j.bioadv.2026.215185
Lv, J., Zhang, J., Jia, X., Wang, Q., Liu, Y., Guo, S., Zhang, D., Chen, C., Hou, B., Ma, Z., et al. (2026) · Industrial & Engineering Chemistry Research · doi:10.1021/acs.iecr.6c03925
Long, Z., Wang, X., & You, L. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c01426
Guest, R., & Guerin, S. (2026) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2026.103522
Meng, Y., Qiao, Z., Liu, L., & Chen, J. (2026) · Composites Part B Engineering · doi:10.1016/j.compositesb.2026.114250
Hayashi, Y., Sugio, K., Sasaki, G., & Okuno, M. (2026) · Algorithms · doi:10.3390/a19100826
Yao, P., Chen, T., Liu, W., & Guo, Z. (2026) · Environmental Research · doi:10.1016/j.envres.2026.125795
Frank, O., Obukeajeta, O. D., Oladosu, M. A., Abah, M. A., Olagbenro, F. S., & Izudike, O. E. (2026) · International Journal of Soft Computing and Engineering · doi:10.35940/ijsce.e3727.16051126
Doust, C. J., & Özkan, E. (2026) · Journal of the Turkish Chemical Society Section A Chemistry · doi:10.18596/jotcsa.1951243
Aham, E. C., Okoye, C. O., Ravikumar, A., Ezenwanne, B. C., Abhadiomhen, S. E., Assumpta Chinyere, A. H. A. M., Zhang, Z., Zhao, H., Jiang, Y., & Xu, Q. H. (2026) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2026.119186
南, 拓., & Yoshida, K. (2026) · MRS Bulletin · doi:10.1557/s43577-026-01198-5
Lu, W.-W., Huang, H., Wang, H., Fan, C., Yu, Z., & Long, H. (2026) · Ceramics International · doi:10.1016/j.ceramint.2026.10.106
Gultekin, M. S. (2026) · Journal of Thermoplastic Composite Materials · doi:10.1177/08927057261498282
Fernandez-Jimenez, C., Capdevila, C., San-Martin, D., Wackerling, D., & Toda‐Caraballo, I. (2026) · Computational Materials Science · doi:10.1016/j.commatsci.2026.115165
Cui, Y., Fu, Y., Liu, K., Liu, X., Xue, C., & Chen, D. (2026) · Journal of Nuclear Materials · doi:10.1016/j.jnucmat.2026.157161
Shi, J., Wu, D., Hu, C., Qiu, P., Fu, C., Wang, J., & Liu, J. (2026) · ChemistrySelect · doi:10.1002/slct.74884
Khairbek, A. A., Alzahrani, A. Y. A., Moussa, S. B., Pooventhiran, T., & Thomas, R. (2026) · Journal of Computational Chemistry · doi:10.1002/jcc.70524 · Cited by 1
“SHAP was chosen because it provides locally accurate, additive attributions that are consistent across model complexities and have a clear game-theoretic foundation [33, 34], and it has become a standard tool for extracting chemical insight from molecular and materials models [35, 36].”
Iram, N., Sharma, R., Wajdan, M., Ahmad, J., Elattar, S., Kumar, A., & El-Rayyes, A. (2026) · Solid State Communications · doi:10.1016/j.ssc.2026.116651
Advances in chemical looping combustion: process design, integration, and operations management
Ronson, D. G., Ali, O. S., Patrón, G. D., & Ricardez‐Sandoval, L. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-40457-3.00001-9
Representing Hydrogels for Machine Learning: Descriptors, Datasets, and the Data Bottleneck
Yavuz, H. İ., & Özbaş, U. K. (2026) · Gels · doi:10.3390/gels12110949
Vedanarayanan, M., Pitchai, C., Chen, C., Kumar, U., & Heng-Jui, L. (2026) · Artificial Intelligence Chemistry · doi:10.1016/j.aichem.2026.100136
Millner, G., Wang, T.-W., Shen, S., Li, Y., & Chen, Y. (2026) · Materials Today Communications · doi:10.1016/j.mtcomm.2026.116478
Tasleem, S., Bongu, C. S., Alyousef, Y. S., & Alsharaeh, E. H. (2026) · International Journal of Hydrogen Energy · doi:10.1016/j.ijhydene.2026.158254
Beyond Partial Readouts: Toward Integrative Mechanism Inference in Catalytic Oxidation
Wu, J., & Yu, H. (2026) · Accounts of Chemical Research · doi:10.1021/acs.accounts.6c00527
Jamal, M. W., Dixit, A., Sharma, R., Shrivastav, N., Almohammedi, A., El‐Rayyes, A., & Elkamchouchi, D. H. (2026) · Energy Storage · doi:10.1002/est2.70550
Li, Y., Chen, T., Ma, P., Chung, T., Zhou, B., Wu, L., Golatkar, A. R., Mukta, S., Little, J. M., Whitley, H. C., et al. (2026) · Science Advances · doi:10.1126/sciadv.aef6378
How semi-deductive structures advance modern physical organic chemistry
García‐Padilla, E., & Qiu, G. (2026) · Advances in physical organic chemistry · doi:10.1016/bs.apoc.2026.10.003
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.