Interpretability in Materials AI — What “Explanation” Means and How It Should Be Evaluated Conceptually

iamrp.net-ollF-1791515266-g434591497 1791515266 Institute for Advanced Materials Research Press info@iamrp.net Institute for Advanced Materials Research Press Journal of Artificial Intelligence for Materials Science J. Artif. Intell. Mater. Sci. 3149-8957 2024 3 2 Interpretability in Materials AI — What “Explanation” Means and How It Should Be Evaluated Conceptually Maria Hernandez Carlos Vega Lucia Torres 2024 10.68159/g434591497 https://iamrp.net/pub/journal/1/article/g434591497 Morgan D, Jacobs R. Opportunities and challenges for machine learning in materials science. Annu Rev Mater Res. 2020;50(1):71-103. Batra R, Song L, Ramprasad R. Emerging materials intelligence ecosystems propelled by machine learning. Nat Rev Mater. 2020;6(8):655-78. Zhong X, Gallagher B, Liu S, Kailkhura B, Hiszpanski A, Han TYJ. Explainable machine learning in materials science. npj Comput Mater. 2022;8(1):204. Suh C, Fare C, Warren JA, Pyzer-Knapp EO. Evolving the materials genome: How machine learning is fueling the next generation of materials discovery. Annu Rev Mater Res. 2020;50:1-25. Gupta V, Choudhary K, Tavazza F, Campbell C, Liao WK, Choudhary A, et al. Cross-property deep transfer learning framework for enhanced predictive analytics on small materials data. Nat Commun. 2021;12(1):6595. Liu T, Barnard AS. The emergent role of explainable artificial intelligence in the materials sciences. Cell Rep Phys Sci. 2023;4(10):101196. Palizhati A, Peczak N, Adcock W, Zuo Y, Deng Z, Ong SP. Interpretable and explainable machine learning for materials science and chemistry. Accounts Mater Res. 2022;3(6):597-607. Szymanski NJ, Bartel CJ, Zeng Y, Tu Q, Gaultois MW, Johansen JM, et al. Accelerating materials discovery using artificial intelligence, high performance computing and robotics. npj Comput Mater. 2022;8(1):84. Li S, Barnard AS. Inverse design of MXenes for high-capacity energy storage materials using multi-target machine learning. Chem Mater. 2022;34(11):4964-74. Li S, Barnard AS. Multi-target neural network predictions of MXenes as high-capacity energy storage materials in a Rashomon set. Cell Rep Phys Sci. 2023;4(11):101633. Gupta V, Liao W, Choudhary A, Agrawal A. Evolution of artificial intelligence for application in contemporary materials science. MRS Commun. 2023;13(5):754-63. Bhakte A, Pakkiriswamy V, Srinivasan R. An explainable artificial intelligence based approach for interpretation of fault classification results from deep neural networks. Chem Eng Sci. 2022;250:117373. Bhakte A, Chakane M, Srinivasan R. Alarm-based explanations of process monitoring results from deep neural networks. Comput Chem Eng. 2023;179:108442. Naser MZ. An engineer’s guide to eXplainable Artificial Intelligence and Interpretable Machine Learning: Navigating causality, forced goodness, and the false perception of inference. Autom Constr. 2021;129:103821. Zhong Y, Tiwari A, Yamaguchi H, Lakhtakia A, Bukkapatnam STS. Identifying the influence of surface texture waveforms on colors of polished surfaces using an explainable AI approach. IISE Trans. 2023;55(7):731-45. Karthikeyan A, Tiwari A, Zhong Y, Bukkapatnam STS. Explainable AI-infused ultrasonic inspection for internal defect detection. CIRP Ann. 2022;71(1):449-52. Yoo J, Cho Y, Jeong B, Choi SH, Kim KK, Lim SC, et al. Explainable Artificial Intelligence Approach to Identify the Origin of Phonon-Assisted Emission in WSe2 Monolayer. Adv Intell Syst. 2023;5(7):2200463. Mankodiya H, Jadav D, Gupta R, Tanwar S. OD-XAI: Explainable AI-based semantic object detection for autonomous vehicles. Appl Sci. 2022;12(11):5310. Mankodiya H, Obaidat MS, Gupta R, Tanwar S. XAI-AV: Explainable artificial intelligence for trust management in autonomous vehicles. Int Conf Commun Comput Cybersecurity Inform. 2021;1-6. Gupta V, Choudhary K, Campbell C, Liao WK, Choudhary A, Agrawal A. MPPredictor: An Artificial Intelligence-Driven Web Tool for Composition-Based Material Property Prediction. J Chem Inf Model. 2023;63(7):1865-71. Yoo J, Cho Y, Kim DH, Kim J, Lee TG, Lee SM, et al. Unraveling the role of Raman modes in evaluating the degree of reduction in graphene oxide via explainable artificial intelligence. Nano Today. 2024;57:102366. Naser MZ, Alavi AH. Error metrics and performance fitness indicators for artificial intelligence and machine learning in engineering and sciences. Arch Struct Constr. 2023;3(4):499-517. Naser MZ, Tapeh ATG. Artificial intelligence, machine learning, and deep learning in structural engineering: a scientometrics review of trends and best practices. Arch Comput Methods Eng. 2023;30(1):115-59. Oommen V, Shukla K, Goswami S, Dingreville R, Karniadakis GE. Learning two-phase microstructure evolution using neural operators and autoencoder architectures. npj Comput Mater. 2022;8(1):190. Zhong Y, Jatav A, Afrin K, Shivaram T, Bukkapatnam STS. Enhanced SpO2 estimation using explainable machine learning and neck photoplethysmography. Artif Intell Med. 2023;145:102685. Zhong Y, Bhattacharya A, Bukkapatnam S. EBLIME: Enhanced Bayesian Local Interpretable Model-agnostic Explanations. arXiv preprint arXiv:2305.00213.2023. Jain S, Kirk R, Lubana ES, Dick RP, Tanaka H, Grefenstette E, et al. Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks. Int Conf Learn Represent. 2023;1-17. Liu T, Tho ZY, Barnard AS. Understanding the importance of individual samples and their effects on materials data using explainable artificial intelligence. Digital Discovery. 2024;3(2):422-35. Naser MZ, Alavi AH. Insights into performance fitness and error metrics for machine learning. arXiv preprint arXiv:2006.00887. 2020. Bhakte A, Kumawat PK, Srinivasan R. Explainable AI methodology for understanding fault detection results during multi-mode operations. Chem Eng Sci. 2024;299:120493. Wang K, Gupta V, Lee CS, Mao Y, Kilic MNT, Li Y, et al. XElemNet: towards explainable AI for deep neural networks in materials science. Sci Rep. 2024;14(1):25178. Li Z, Li S, Birbilis N. A machine learning-driven framework for the property prediction and generative design of multiple principal element alloys. Mater Today Commun. 2024;38:107940. Suh HC, Yoo J, Yeo K, Kim DH, Won YS, Kim T, et al. Probing nanoscale structural perturbation in a WS2 monolayer via explainable artificial intelligence. Appl Phys Rev. 2025;12(2):021304.