Knowledge-integrated machine learning for materials: lessons from gameplaying and robotics

• Published in: Nature reviews. Materials Vol. 8; no. 4; pp. 241 - 260
• Main Authors: Hippalgaonkar, Kedar, Li, Qianxiao, Wang, Xiaonan, Fisher, John W., Kirkpatrick, James, Buonassisi, Tonio
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group 01.04.2023
• Subjects: Algorithms; Knowledge; Knowledge representation; Machine learning; Materials research; Materials science; Robotics; Software; Task complexity; Workflow
• ISSN: 2058-8437; 2058-8437
• DOI: 10.1038/s41578-022-00513-1

As materials researchers increasingly embrace machine-learning (ML) methods, it is natural to wonder what lessons can be learned from other fields undergoing similar developments. In this Review, we comparatively assess the evolution of applied ML in materials research, gameplaying and robotics. We observe ML being integrated into each field in three phases: first into discrete hardware and software tools (toolset integration); second across different steps in a workflow (workflow integration); and third through the incorporation, generation and representation of generalizable knowledge beyond any one study (knowledge integration). We identify transferrable lessons from gameplaying and robotics to materials research, including adaptive and accessible automation, the gamification of grand challenges to focus community efforts on specific workflow integrations and motivate benchmarks and canonical datasets, and the adoption of hybrid (data-based and model-based) algorithms that combine domain expertise and current learning to economically address high-complexity tasks. We identify opportunities for researchers from different fields to collaborate, including novel ways to represent and integrate a rich but heterogeneous corpus of knowledge (such as heuristics, physical laws, literature or data) with ML algorithms to create new knowledge, and safe and equitable deployment of technologies with societally beneficial outcomes.Machine learning is increasingly popular in materials science research. This Review generalizes learnings from applied machine learning in robotics and gameplaying and extends it to materials science. In particular, hybrid approaches combining model-based and data-driven models are seeding the transition from the application of machine learning to discrete tools and workflows towards emergent knowledge.