Scientific AI in Materials Science: a Path to a Sustainable and Scalable Paradigm
Brian L. DeCost, Jason R. Hattrick-Simpers, Zachary T. Trautt, Aaron G. Kusne, Martin L. Green, Eva Campo
Recent years have seen an ever-increasing trend in the use of machine learning (ML) and artificial intelligence (AI) methods by the materials science, condensed matter physics, and chemistry communities. This perspective article identifies key scientific, technical, and social opportunities that the materials community must prioritize to consistently develop and leverage Scientific AI (SciAI) to allow current materials-limited technologies to progress. Figure 1 shows the intersection of these growth opportunities with our proposed paths forward; strongly-related pairs are highlighted in blue. The opportunities are roughly sorted from scientific/technical (e.g. development of robust, physically meaningful multiscale material representations) to social (e.g. promoting an AI-ready workforce). The proposed paths forward range from developing new infrastructure and capabilities to deploying it in industry and academia. We provide a brief introduction to AI in materials science and engineering, followed by detailed discussions of each of the opportunities and paths forward, emphasizing the highlighted relationships
, Hattrick-Simpers, J.
, Trautt, Z.
, Kusne, A.
, Green, M.
and Campo, E.
Scientific AI in Materials Science: a Path to a Sustainable and Scalable Paradigm, Nature Materials, [online], https://doi.org/10.1088/2632-2153/ab9a20
(Accessed October 25, 2021)