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 301–400 of 435
Symmetry inspired learning of governing equations from noisy data
Chen, H., & Xiao, D. (2026) · Physics of Fluids · doi:10.1063/5.0311831 · Cited by 1
Artificial Intelligence Nanocomposite Synergy for Next-Generation Fuel Desulfurization
Kostas, R. Y., Bozbeyoğlu, P., Altuner, E. E., & Elmas, M. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-5966-3.ch010
Lin, H., Song, H., Zou, Y., Huang, Y., Lv, F., Wang, S., & Bai, H. (2026) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c24558
Toward Trustworthy AI: Explainable and Robust Machine Learning for Medical ApplicationsPreprint
Yu, T., Tao, P., & Ru, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5328192 · Cited by 1
Intelligent Methods for Materials Discovery and Design
Agrawal, A., Singh, J., Jain, A., Tiwari, A. K., Kushwah, A. S., & Verma, N. K. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6127-7.ch001
Zhang, Y., Sadiq, M., Fraz, M. M., aldhahri, E. A., Almazroi, A. A., Iqbal, M., Hayat, A., Geng, Y., Algamdi, A. S. R., Noreen, A., et al. (2026) · Sustainable materials and technologies · doi:10.1016/j.susmat.2026.e01949 · Cited by 2
A crystal graph to vector approach for predicting magnetic properties
Singh, S. K., Sharma, A., & Kashyap, A. (2026) · Scientific Reports · doi:10.1038/s41598-026-40902-y · Cited by 1
From Data to Discovery: Challenges and Solutions in AI-Driven Materials Science
Dam, H., Kino, H., & Miyake, T. (2026) · Journal of the Physical Society of Japan · doi:10.7566/jpsj.95.042001 · Cited by 1
Jagadale, S. K., Pagale, M., Bokefode, P., Dighole, S., Ajmera, L., Thakur, I., Rathod, M. S., & Rathod, S. M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6505823
Kondo, S., Kurokawa, Y., Kutsukake, K., Takeno, S., Katsube, R., & Usami, N. (2026) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ae5f26
Machine learning-based closed-loop for optimizing HOMO–LUMO gap in diarylethene
Nguyen, L. T. H., Fabbrini, E., Olenko, A. Y., Staykov, A., & Cesana, P. (2026) · Physical Chemistry Chemical Physics · doi:10.1039/d6cp00402d
Bajpai, A., Ratzker, B., Cavaliere, P. D., & Raabe, D. (2026) · Advanced Science · doi:10.1002/advs.75498
“…advances in interpretable machine learning provide constrained function classes that can represent such multivariable dependencies while enforcing physically motivated shape constraints, which is essential when outcomes are intended to support hydrogen allocation and operating policy [ 42, 43 ].”
From Local Atomic Structure to X-ray Spectra: Absorber-Centric Machine-Learning Encoding
Pope, T. J., Li, B., Junkawitsch, H., Bande, A., & Penfold, T. J. (2026) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.6c01127
Singha, S., Aunoy, M. H., Datta, S., & Chowdhury, A. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491717
Machine learning in theoretical study of single-molecule magnets: Current status and challenges
Zheng, S., Zou, Z., Yifan, D., Hong, W. B. J., & JIANG, H. (2026) · Acta Physica Sinica · doi:10.7498/aps.75.20260221
Li, A., Bian, F., Guo, J., Gong, C., Guo, Y., Zuo, C., Chen, J., Hu, X., & Xu, Z. (2026) · Artificial Intelligence Chemistry · doi:10.1016/j.aichem.2026.100124 · Cited by 1
Naser, M. Z., & Rangaraju, P. R. (2026) · Materials Research Bulletin · doi:10.1016/j.materresbull.2026.114251
Attention-Enhanced Surrogate Modeling for Robust and Interpretable Multilayer Photonic Film Design
Tan, H., & Gui, X. (2026) · International Conference on the Software Process · doi:10.1109/icsp69961.2026.11540978
“Second, even when a neural surrogate achieves low prediction error, it is still necessary to examine whether the learned mapping is physically meaningful rather than merely data-correlated, especially in photonics applications where interpretability is closely related to trustworthiness [8], [9].”
Elalaoui, O., Abdennaji, T. S., Alanazi, A. O., Fatnassi, A., Tipu, R. K., & Pandya, K. S. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10662-z · Cited by 2
Wu, C., Xu, D., Li, Y., Liu, T., Xie, J., Luo, W., Wu, Z., Su, Y., & Cao, D. (2026) · Journal of Materials Chemistry A · doi:10.1039/d6ta00217j
Zhao, Z., Chen, Z., Wang, Z., Chen, H., Dai, G., & Zeng, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6909826
Zhu, L., Qin, X., Chen, J., Wu, T., Zhang, L., & Chen, Z. (2026) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.6c00890
Никульченков, Н. Н., & Milyutin, V. A. (2026) · Journal of Materials Science · doi:10.1007/s10853-026-12999-z
“In other words, although ML algorithms can successfully solve important problems in materials science, they usually do not lead to new scientific information in itself that could bring us closer to understanding natural phenomena and laws [15].”
Multimodal Learning with Rashomon Analysis for Battery Discharge Capacity Prediction
Gong, J., Wang, L. W., Zhu, T., Butler, K. T., & Li, S. (2026) · Advanced Intelligent Discovery · doi:10.1002/aidi.70140
Self-citationExplainable distributional structure of MXene compositions revealed by Shapley analysis
Liu, T., & Barnard, A. S. (2026) · APL Machine Learning · doi:10.1063/5.0326966
Y, B., Li, J., Zhang, Q., Chen, F., Li, B., Tian, Z., & Chen, L. (2026) · Materials Genome Engineering Advances · doi:10.1002/mgea.70079
Huang, Z., Fu, X., & Qi, R. (2026) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.6c05445
Baumer, C., Mai, C., Eisentraut, L., Bund, A., & Buettner, R. (2026) · Advanced Engineering Materials · doi:10.1002/adem.70988
“The present study adopts this interpretability-focused perspective by combining SHAP-based global and interaction analyses with partial dependence plots to link ML results to electrochemical principles [31, 32].”
Preaching Meaning, Practicing the Motions: A Critical Analysis of XAI Research
van der Linden, I., & Ghebreab, S. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812356
Jin, S., Wang, Z., Li, M., & Deng, Z. (2026) · Small Structures · doi:10.1002/sstr.70446 · Cited by 2
“A network may correctly classify the onset of lithium plating or forecast capacity fade but often offers little explanation of which structural or dynamical features drive the prediction [177].”
Kong, X., Meharban, F., Tan, L., Xu, J., Wu, X., Lin, C., Chen, S., Jiang, Z., Li, X., & Luo, W. (2026) · Green Energy & Environment · doi:10.1016/j.gee.2026.06.017
Zhao, R., Liu, Q., Lin, C., Xie, J., Li, D., Gou, R., Gong, L., & Gao, S. (2026) · ACS Omega · doi:10.1021/acsomega.6c04000
Wang, W., Ruan, H.-O., Butler, K. T., Kumada, A., & Sato, M. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c02120
Self-citationInformation science for materials science
Rajan, K. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-22256-6.00001-4
Díaz-Tato, L., Carrera, L. A. I., Hugo, M. Á., Rubio, C. A. N., García-Barajas, M. G., Velásquez, F. A. C., de Paz, J. P. Z., Rodríguez‐Reséndiz, J., & Rodríguez-Castellanos, E. A. (2026) · Inorganics · doi:10.3390/inorganics14070177
“This information is valuable for industrial decision-making because it allows operators to define acceptable variability windows, identify critical control parameters, and adjust formulations before defects or performance losses occur [128].”
Materials informatics across the length scales
Nasir, J. A., Kavak, H., Der, O., Erçetin, A., Akagić, A., Friis, J., Bleken, F. L., Lorenzoni, A., Mercuri, F., Woodley, S. M., et al. (2026) · Machine Learning Engineering · doi:10.1088/3049-4761/ae850a · Cited by 1
“For instance, model interpretability is a significant challenge in materials informatics [74, 75].”
Self-citationInterpretable machine-learning models for predicting elasticity and ductility of inorganic materials
Han, Y., Pan, Z., & Zhao, R. (2026) · Physical Review Materials · doi:10.1103/3c4b-phhy
Ilina, Т. S., Torianik, S. V., Zakhidov, D. S., & Kiselev, D. A. (2026) · Modern Electronic Materials · doi:10.3897/j.moem.12.2.194213
Liu, Y., Tan, Z., Pan, Y., Yin, R., Zhang, H., & Li, W. (2026) · Water Research · doi:10.1016/j.watres.2026.126473
Khalid, S., Faseeh, M., Khan, M. A., Song, H., Naqvi, S. S. A., Ko, H., & Kim, D.-H. (2026) · Journal of Materiomics · doi:10.1016/j.jmat.2026.101282
Unveiling physical insight through XAI-based correlative spectroscopy
Yoo, J., & Jeong, M. S. (2026) · Current Applied Physics · doi:10.1016/j.cap.2026.07.008
Zhang, H., Xing, W., & Ding, P. (2026) · Review of Materials Research · doi:10.1016/j.revmat.2026.100247
Wang, Y., & Chan, Y. (2026) · Langmuir · doi:10.1021/acs.langmuir.6c02154
Klenam, D. E. P., Asumadu, T. K., Bodunrin, M. O., & Soboyejo, W. O. (2026) · Journal of Alloys and Compounds Communications · doi:10.1016/j.jacomc.2026.100226 · Cited by 1
Functional machine learning modeling of electronic bandgap
Baninajarian, S., Hashemifar, S. J., Abedi, S., Haghighi, M. S., & Levchenko, S. V. (2026) · The Journal of Chemical Physics · doi:10.1063/5.0325183
Shoaib, S. A., & SaifAddin, B. K. (2026) · Crystals · doi:10.3390/cryst16080484
SPEAR-EELS: Physically Constrained Attention for Interpretable STEM Spectroscopy
Raghavan, A., Pratiush, U., & Kalinin, S. V. (2026) · Microscopy and Microanalysis · doi:10.1093/mam/ozag053.339
Oziel, J., Selvaratnam, B., Jaffal, E. I., & Oliynyk, A. O. (2026) · Solid State Communications · doi:10.1016/j.ssc.2026.116540 · Cited by 1
Hoşavcı, R., & Malkoç, D. (2026) · Journal of Data Analytics and Artificial Intelligence Applications · doi:10.26650/d3ai.1968176
Long, Q., Zhao, X., Xia, W., Yue, Q., Xie, P., Zhang, X., Gu, Y., & Zhang, Z. (2026) · Progress in Natural Science Materials International · doi:10.1016/j.pnsc.2026.04.011
Azeem, M. M., & Zhong, Y. (2026) · Nuclear Instruments and Methods in Physics Research Section B Beam Interactions with Materials and Atoms · doi:10.1016/j.nimb.2026.166275
Yeom, H., Kim, Y.-S., & Na, K. (2026) · Advanced Functional Materials · doi:10.1002/adfm.77430
Li, Z., & Mohd, N. (2026) · Materials chemistry and physics. · doi:10.1016/j.macse.2026.100076
Machine Learning Meets Photocatalytic Water Splitting for Sustainable Hydrogen Production
Yoon, H., Cho, J. H., Ong, W., & Kim, S. Y. (2026) · ChemPhotoChem · doi:10.1002/cptc.70239
Xiong, Z., Meng, W., Yang, T., Zhu, J., Yuan, Z., Shang, Y., Wu, J., Li, J., Feng, Z., Mao, L., et al. (2026) · Energy & Environmental Science · doi:10.1039/d6ee02587k
Peng, W., Hayashi, S., García, A. C., Fang, L., Takeguchi, M., Xu, Y., & Sakaushi, K. (2026) · Science and Technology of Advanced Materials · doi:10.1080/14686996.2026.2713992
“A data-driven approach with inter-pretability and/or explainability is essential for ‘opening’ black-boxes of present standard AI-driven material discovery [24–26].”
Molecular and polymer representations for machine learning
Lin, C., Taylor, J., Barnard, A. S., Connal, L. A., Pollard, B. L., & Parker, A. J. (2026) · Digital Discovery · doi:10.1039/d6dd00109b · Cited by 2
Resolving Chemically Inequivalent 11B NMR Sites via Interpretable Hybrid Machine Learning
Li, P., Gao, B., Wang, S., Liu, W., Wei, Z., Yin, G., & Li, Y. (2026) · JACS Au · doi:10.1021/jacsau.6c00935
Learning Work Function via Implicit Reasoning on Electrostatic Potential Landscapes
Wan, H., Wu, Y., Su, T., & Pan, D. (2026) · Advanced Science · doi:10.1002/advs.77166
“Although high attention weights do not directly equate to causal discovery, they imply that the features of those specific elemental nodes carry higher signal strength within the model’s decision path [ 44 ].”
Grey Wolf Optimization Inverse Mix Design of Steel Slag Asphalt Mixtures
Song, H., Wang, Z., & Zheng, Y. (2026) · Materials · doi:10.3390/ma19163497
“A key challenge is therefore to integrate interpretable artificial intelligence with materials science while maintaining predictive accuracy and extracting physically meaningful patterns from empirical data [27–29].”
Miyan, N., Paswan, R., & Das, S. (2026) · Materials Today Communications · doi:10.1016/j.mtcomm.2026.115972
Yu, X., Zhang, Y., Liang, L., Yan, X., Yao, H., Li, Z., Wang, Z., Hu, X., wu, G., hu, X., et al. (2026) · Applied Optics · doi:10.1364/ao.605984
Shudo, Y., Taguchi, R., Akashi, M., Shimizu, S., Kawamoto, T., & Takahashi, A. (2026) · Journal of Materials Chemistry A · doi:10.1039/d6ta04505g
Molaverdi, F., Rasa, A. Y., Shehu, L., & Song, Y. (2026) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2026.190393
Li, S., Zhu, T., Deng, W., Zhuang, Z., Xu, X., Wei, Y., Barnard, A. S., & Butler, K. T. (2026) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2026.103518
Self-citationShiravani, F., Patil, D., Estakhr, O., Zolghadr, A. R., & Tashkhourian, J. (2026) · ACS Applied Energy Materials · doi:10.1021/acsaem.6c01544
From Explainable Machine Learning to Physics-Guided Design Rules for Inorganic PhosphorsPreprint
Nematov, D., Kayumov, M., Ashurov, A., Burkhonzoda, A., Murodzoda, S., Kurboniyon, M. S., Wen, N., Li, J., Ivansyah, A. L., Wang, P., et al. (2026) · Preprints.org · doi:10.20944/preprints202608.1728.v2
Wang, X., Niu, S., Li, D., Wang, Z., Zhou, H., Dong, X., & Yao, Y. (2026) · Energy storage materials · doi:10.1016/j.ensm.2026.105511
Architectural Optimization of Multilayer Thermal Barrier Coatings
Ashofteh, A., & Seifollahpour, S. (2026) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.6c14239
From Prediction to Physical Meaning in Materials AI
Li, M., & Lin, P. (2026) · ACS Materials Au · doi:10.1021/acsmaterialsau.6c00170
Algorithmic Simplicity as Scientific Virtue: A Conceptual Tension in Materials AI Design
Rahman, S., Zaki, A., Huda, N., Faisal, A., & Wei, L. (2025) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/k354459599
The Treatment of Absence and Null Results in Materials Machine Learning Literature: A Review Study
Huy, N. T., Minh, P. Q., & Bich, L. T. (2022) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/c772411799
Temporal Generalization in Materials AI — What We Know About Model Aging and Drift
Menon, R., Nair, A., Pillai, M., & Varma, S. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/k629752182
Brooks, D., Carter, A., Moore, E., & Grant, O. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/k194905171
Hernandez, M., & Vega, C. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/w105180400
Benchmarking Practices in Materials Artificial Intelligence — What Is Measured and What Is Missed
Amrani, F. Z., Benali, Y., & El-Haddad, S. (2026) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/o900345807
Kowalska, A., Nowak, P., Zielinski, T., & Mazur, K. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/o220486108
Scientific Blind Spots Introduced by Feature Engineering in Materials Informatics
Amrani, F. Z., Benali, Y., & El-Haddad, S. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/o637133842
Failure Modes in Materials AI Explanations: A Conceptual Catalog and Prevention Principles
Nakamura, H., & Kato, Y. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/p903378881
Explainable AI for Interpretable Structure–Property Maps in Polymer Blend Systems
Martin, C., Robert, J., & Bernard, S. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/p209601272
Amrani, F. Z., Benali, Y., & El-Haddad, S. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/z805552631
Huy, N. T., Bich, L. T., & Minh, P. Q. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/e225827767
Conceptual Foundations for Value-Sensitive Design of Materials AI Systems
Dupont, C., & Martin, J. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/e174870223
Exploration without Explanation: A Conceptual Critique of Black-Box Materials Discovery
Tanaka, H., Sato, Y., Mori, K., & Okabe, R. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/p383264882
Explainability Drift in Iterative Materials AI Workflows: A Conceptual Failure Analysis
Andrade, L., & Lopes, M. (2025) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/j640776843
Governance and Responsible Use of Materials AI — Standards, Transparency, and Risk Management
Amrani, F. Z., Benali, Y., El-Haddad, S., & Idrissi, K. O. (2025) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/h097101046
Meyer, L., Braun, S., & Schmid, A. (2025) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/j660053005
Small-Data and Sparse-Regime Learning in Materials AI — Methods, Assumptions, and Limits
Hernandez, M., Vega, C., & Torres, L. (2026) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/z932480750
Papadopoulos, G., & Georgiou, E. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/i095251554
Pereira, L., & Martins, B. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/q969725355
Tanaka, H., Sato, Y., Mori, K., & Okabe, R. (2026) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/p251238849
Meyer, L., Schmid, A., & Braun, S. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/m146031544
A Conceptual Distinction between Generalization and Transfer in Materials Machine Learning
中村博志, & Kato, Y. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/q862149980
de Moraes, B. M., Fuente-Ballesteros, A., Valente, F. J., & Zuin, V. G. (2026) · Sustainability & Circularity NOW · doi:10.1055/a-2939-5948
Materials AI as Policy Actor: A Conceptual Framework for Downstream Decision Impact
Hernandez, M., Vega, C., & Torres, L. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/o494214876
The Curse of Optimality: When Perfect Optimization Undermines Scientific Understanding
Abdelrahman, N., Hassan, K., & El-Kholy, A. (2023) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/z868299712
The Problem of Convergent Scientific Narratives in Single-Model Materials Regimes
Boateng, S., Mensah, K., Asante, K., & Owusu, L. (2026) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/e712760163
What Counts as Knowledge in AI-Driven Materials Science? A Philosophical and Practical Reframing
Hernandez, M., & Vega, C. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/a045179042
Hernandez, M., Vega, C., & Torres, L. (2024) · Journal of Artificial Intelligence for Materials Science · doi:10.68159/g434591497
Failure Visibility and Epistemic Accountability in Self-Driving Materials Engineering
Andrade, L., & Lopes, M. (2025) · Journal of Computational and Data-Driven Materials Engineering · doi:10.68159/k302210786
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.