Materials cartography: A forward-looking perspective on materials representation and devising better maps

• Published in: APL machine learning Vol. 1; no. 2; pp. 020901 - 020901-11
• Main Authors: Torrisi, Steven B., Bazant, Martin Z., Cohen, Alexander E., Cho, Min Gee, Hummelshøj, Jens S., Hung, Linda, Kamat, Gaurav, Khajeh, Arash, Kolluru, Adeesh, Lei, Xiangyun, Ling, Handong, Montoya, Joseph H., Mueller, Tim, Palizhati, Aini, Paren, Benjamin A., Phan, Brandon, Pietryga, Jacob, Sandraz, Elodie, Schweigert, Daniel, Shao-Horn, Yang, Trewartha, Amalie, Zhu, Ruijie, Zhuang, Debbie, Sun, Shijing
• Format: Journal Article
• Language: English
• Published: AIP Publishing LLC 01.06.2023
• ISSN: 2770-9019; 2770-9019
• DOI: 10.1063/5.0149804

Machine learning (ML) is gaining popularity as a tool for materials scientists to accelerate computation, automate data analysis, and predict materials properties. The representation of input material features is critical to the accuracy, interpretability, and generalizability of data-driven models for scientific research. In this Perspective, we discuss a few central challenges faced by ML practitioners in developing meaningful representations, including handling the complexity of real-world industry-relevant materials, combining theory and experimental data sources, and describing scientific phenomena across timescales and length scales. We present several promising directions for future research: devising representations of varied experimental conditions and observations, the need to find ways to integrate machine learning into laboratory practices, and making multi-scale informatics toolkits to bridge the gaps between atoms, materials, and devices.