Interpretable and Explainable Machine Learning for Materials Science and Chemistry
Open accessThe DOI matches its Crossref record; 62 of the 62 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. (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 3,781
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
The Book of Why: The New Science of Cause and Effect
Goldberg, L. R. (2019) · Notices of the American Mathematical Society · doi:10.1090/noti1912 · Cited by 1,655
Machine Learning Interatomic Potentials as Emerging Tools for Materials Science
Deringer, V. L., Caro, M. A., & Csányi, G. (2019) · Advanced Materials · doi:10.1002/adma.201902765 · Cited by 1,036
Interpretable machine learning
Parliamentary Office of Science and Technology, & Christie, L. (2020) · doi:10.58248/pn633 · Cited by 952
Ouyang, R., Curtarolo, S., Ahmetcik, E., Scheffler, M., & Ghiringhelli, L. M. (2018) · Physical Review Materials · doi:10.1103/physrevmaterials.2.083802 · Cited by 944
(2013) · American Economic Review · doi:10.1257/aer.103.4.i · Cited by 818
Best practices in machine learning for chemistry
Artrith, N., Butler, K. T., Coudert, F.-X., Han, S., Isayev, O., Jain, A., & Walsh, A. (2021) · Nature Chemistry · doi:10.1038/s41557-021-00716-z · Cited by 505
Self-citationWetzel, S. J. (2017) · Physical Review E · doi:10.1103/physreve.96.022140 · Cited by 488
Machine learning modeling of superconducting critical temperature
Stanev, V., Oses, C., Kusne, A. G., Rodriguez, E., Paglione, J., Curtarolo, S., & Takeuchi, I. (2018) · npj Computational Materials · doi:10.1038/s41524-018-0085-8 · Cited by 451
Too much, too little, or just right? Ways explanations impact end users' mental models
Kulesza, T., Stumpf, S., Burnett, M., Yang, S., Kwan, I., & Wong, W.-K. (2013) · 2013 IEEE Symposium on Visual Languages and Human Centric Computing · doi:10.1109/vlhcc.2013.6645235 · Cited by 388
Towards better understanding of gradient-based attribution methods for Deep Neural Networks
Ancona, M., Ceolini, E., Öztireli, C., & Groß, M. H. (2017) · Zurich Open Repository and Archive (University of Zurich) · doi:10.3929/ethz-b-000249929 · Cited by 368
Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution
Pearl, J. (2018) · Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining · doi:10.1145/3159652.3176182 · Cited by 338
Oviedo, F., Ren, Z., Sun, S., Settens, C., Liu, Z., Hartono, N. T. P., Ramasamy, S., DeCost, B. L., Tian, S. I. P., Romano, G., et al. (2019) · npj Computational Materials · doi:10.1038/s41524-019-0196-x · Cited by 327
Self-citationInterpretML: A Unified Framework for Machine Learning Interpretability
Nori, H., Jenkins, S., Koch, P., & Caruana, R. (2019) · arXiv · doi:10.48550/arxiv.1909.09223 · Cited by 322
Extraction of organic chemistry grammar from unsupervised learning of chemical reactions
Schwaller, P., Hoover, B., Reymond, J.-L., Strobelt, H., & Laino, T. (2021) · Science Advances · doi:10.1126/sciadv.abe4166 · Cited by 296
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Verma, S., Boonsanong, V., Hoang, M., Hines, K. E., Dickerson, J. P., & Shah, C. (2020) · arXiv · doi:10.48550/arxiv.2010.10596 · Cited by 267
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Verma, S., Boonsanong, V., Hoang, M., Hines, K., Dickerson, J., & Shah, C. (2024) · ACM Computing Surveys · doi:10.1145/3677119 · Cited by 255
CXPlain: Causal Explanations for Model Interpretation under UncertaintyPreprint
Schwab, P., & Karlen, W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12336 · Cited by 223
How machine learning can help select capping layers to suppress perovskite degradation
Hartono, N. T. P., Thapa, J., Tiihonen, A., Oviedo, F., Batali, C., Yoo, J. J., Liu, Z., Li, R., Marrón, D. F., Bawendi, M. G., et al. (2020) · Nature Communications · doi:10.1038/s41467-020-17945-4 · Cited by 189
Self-citationVasudevan, R. K., Choudhary, K., Mehta, A., Smith, R., Kusne, G., Tavazza, F., Vlcek, L., Ziatdinov, M., Kalinin, S. V., & Hattrick-Simpers, J. (2019) · MRS Communications · doi:10.1557/mrc.2019.95 · Cited by 185
Tang, B., Kramer, S. T., Fang, M., Qiu, Y., Wu, Z., & Xu, D. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-020-0414-z · Cited by 163
A data fusion approach to optimize compositional stability of halide perovskites
Sun, S., Tiihonen, A., Oviedo, F., Liu, Z., Thapa, J., Zhao, Y., Hartono, N. T. P., Goyal, A., Heumueller, T., Batali, C., et al. (2021) · Matter · doi:10.1016/j.matt.2021.01.008 · Cited by 158
Self-citationUnsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
Hsu, W.-N., Zhang, Y., & Glass, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.07902 · Cited by 148
Model agnostic generation of counterfactual explanations for molecules
Wellawatte, G. P., Seshadri, A., & White, A. D. (2022) · Chemical Science · doi:10.1039/d1sc05259d · Cited by 143
Shapley explainability on the data manifoldPreprint
Frye, C., de Mijolla, D., Begley, T., Cowton, L. R., Stanley, M. J., & Feige, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.01272 · Cited by 136
Takahashi, A., Kumagai, Y., Miyamoto, J., Mochizuki, Y., & Oba, F. (2020) · Physical Review Materials · doi:10.1103/physrevmaterials.4.103801 · Cited by 112
Esterhuizen, J. A., Goldsmith, B. R., & Linic, S. (2020) · Chem · doi:10.1016/j.chempr.2020.09.001 · Cited by 107
Machine Learning and Causal Inference for Policy Evaluation
Athey, S. C. (2015) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2783258.2785466 · Cited by 101
Modeling the dielectric constants of crystals using machine learning
Morita, K., Davies, D. W., Butler, K. T., & Walsh, A. (2020) · The Journal of Chemical Physics · doi:10.1063/5.0013136 · Cited by 88
Self-citation(2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33391-1 · Cited by 79
Extracting Interpretable Physical Parameters from Spatiotemporal Systems Using Unsupervised Learning
Lu, P. Y., Kim, S., & Marin Soljacic, A. (2020) · Physical Review X · doi:10.1103/physrevx.10.031056 · Cited by 66
Korolev, V., Mitrofanov, A. A., Marchenko, E. I., Eremin, N. N., Tkachenko, V., & Kalmykov, S. N. (2020) · Chemistry of Materials · doi:10.1021/acs.chemmater.0c02468 · Cited by 62
Modeling the dielectric constants of crystals using machine learning
Morita, K., Davies, D. W., Butler, K. T., & Walsh, A. (2021) · ePubs (Science and Technology Facilities Council, Research Councils UK) · Cited by 61
Self-citationDistributed representations of atoms and materials for machine learning
Antunes, L. M., Grau‐Crespo, R., & Butler, K. T. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00729-3 · Cited by 55
Self-citationRen, Z., Oviedo, F., Thway, M., Tian, S. I. P., Wang, Y., Xue, H., Perea, J. D., Layurova, M., Heumueller, T., Birgersson, E., et al. (2020) · npj Computational Materials · doi:10.1038/s41524-020-0277-x · Cited by 54
Self-citationData-driven discovery of free-form governing differential equationsPreprint
Atkinson, S., Subber, W., Wang, L., Khan, G., Hawi, P., & Ghanem, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.05117 · Cited by 51
Data-Driven Discovery of Photoactive Quaternary Oxides Using First-Principles Machine Learning
Davies, D. W., Butler, K. T., & Walsh, A. (2019) · Chemistry of Materials · doi:10.1021/acs.chemmater.9b01519 · Cited by 49
Self-citationDeep Learning for Molecules and Materials
White, A. D. (2022) · Living Journal of Computational Molecular Science · doi:10.33011/livecoms.3.1.1499 · Cited by 49
Entropy-based active learning of graph neural network surrogate models for materials properties
Allotey, J., Butler, K. T., & Thiyagalingam, J. (2021) · The Journal of Chemical Physics · doi:10.1063/5.0065694 · Cited by 44
Self-citationInterpretable Artificial Intelligence: A Perspective of Granular Computing
(2021) · Studies in computational intelligence · doi:10.1007/978-3-030-64949-4 · Cited by 44
Ziatdinov, M., Nelson, C. T., Zhang, X., Vasudevan, R. K., Eliseev, E., Morozovska, A. N., Takeuchi, I., & Kalinin, S. V. (2020) · npj Computational Materials · doi:10.1038/s41524-020-00396-2 · Cited by 39
He, H., & Pathak, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.09684 · Cited by 36
Naik, R. R., Tiihonen, A., Thapa, J., Batali, C., Liu, Z., Sun, S., & Buonassisi, T. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00751-5 · Cited by 31
Self-citationFrom atomically resolved imaging to generative and causal models
Kalinin, S. V., Ghosh, A., Vasudevan, R. K., & Ziatdinov, M. A. (2022) · Nature Physics · doi:10.1038/s41567-022-01666-0 · Cited by 29
Kalinin, S. V., Steffes, J., Liu, Y., Huey, B. D., & Ziatdinov, M. A. (2021) · Nanotechnology · doi:10.1088/1361-6528/ac2f5b · Cited by 28
Trivedi, A., Robinson, C., Blazes, M., Ortiz, A., Desbiens, J., Gupta, S., Dodhia, R., Bhatraju, P. K., Liles, W. C., Kalpathy-Cramer, J., et al. (2022) · PLOS ONE · doi:10.1371/journal.pone.0274098 · Cited by 28
BERT Learns (and Teaches) ChemistryPreprint
Payne, J., Srouji, M. S., Yap, D. A., & Kosaraju, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.16012 · Cited by 26
Robinson, C., Trivedi, A., Blazes, M. S., et al. (2021) · medRxiv · doi:10.1101/2021.02.11.20196766 · Cited by 12
Ziatdinov, M. A., & Kalinin, S. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.10180 · Cited by 9
Model agnostic generation of counterfactual explanations for moleculesPreprint
Wellawatte, G. P., Seshadri, A., & White, A. D. (2021) · ChemRxiv · doi:10.26434/chemrxiv-2021-4qkg8-v2 · Cited by 4
Naik, R. R., Tiihonen, A., Thapa, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10951 · Cited by 1
Liu, Y., Ziatdinov, M. A., & Kalinin, S. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06888 · Cited by 1
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
Explainable machine learning in materials science
Zhong, X., Gallagher, B., Liu, S., Kailkhura, B., Hiszpanski, A., & Han, T. Y.-J. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00884-7 · Cited by 501
“This work of Oviedo et al. 22 is an example of explaining model processing to achieve better performance.”
BackgroundMethodMersha, M., Lam, K., Wood, J., AlShami, A. K., & Kalita, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128111 · Cited by 237
“Explainability in chemistry and material science increases beyond simply understanding and analyzing model outputs; it encompasses understanding the rationale behind the model predictions [196].”
BackgroundApplied machine learning as a driver for polymeric biomaterials design
McDonald, S. M., Augustine, E. K., Lanners, Q., Rudin, C., Catherine Brinson, L., & Becker, M. L. (2023) · Nature Communications · doi:10.1038/s41467-023-40459-8 · Cited by 167
“…feature importance like deep learning methods),interpretableMLalgorithms(i.e.,modelswhichinformation about feature importance can be extracted like random forest algorithms) create models that are more transparent, easier to trouble-shoot, and facilitate understanding of the chemical system 70,71 .”
BackgroundMachine Learning for Perovskite Solar Cells and Component Materials: Key Technologies and Prospects
Liu, Y., Tan, X., Liang, J., Han, H., Xiang, P., & Yan, W. (2023) · Advanced Functional Materials · doi:10.1002/adfm.202214271 · Cited by 174
When Machine Learning Meets 2D Materials: A Review
Lu, B., Xia, Y., Ren, Y., Miaomiao, X., Zhou, L., Vinai, G., Morton, S. A., Wee, A. T. S., van der Wiel, W. G., Zhang, W., et al. (2024) · Advanced Science · doi:10.1002/advs.202305277 · Cited by 200
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.