Machine Learning for Materials Scientists: An Introductory Guide toward Best Practices

This Methods/Protocols article is intended for materials scientists interested in performing machine learning-centered research. We cover broad guidelines and best practices regarding the obtaining and treatment of data, feature engineering, model training, validation, evaluation and comparison, popular repositories for materials data and benchmarking data sets, model and architecture sharing, and finally publication. In addition, we include interactive Jupyter notebooks with example Python code to demonstrate some of the concepts, workflows, and best practices discussed. Overall, the data-driven methods and machine learning workflows and considerations are presented in a simple way, allowing interested…

• NS
  National Science Foundation

  Awards: CMMI-1562226, DMR-1651668, 18-47701, 1651668, DE-AC02-05CH11231, 1562226, CER 19-11311, DMR 18-47701
• UD
  U.S. Department of Energy

  Awards: -AC02-05CH11231, 05CH11231, KC23MP, AC02-05CH11231, DE-AC07-05ID145142, DE-AC02, DE-AC02-05CH11231, DE-AC02-
• WF
  Welch Foundation

  Award: E-1981
• DA
  Deutscher Akademischer Austauschdienst

  Award: 57438025
• DF
  Deutsche Forschungsgemeinschaft

  Award: DE-AC02-05CH11231
• TU
  Technische Universität Berlin
• OO
  Office of Science

  Awards: AC02-05CH11231, -AC02-05CH11231, DE-AC02
• IO
  Idaho Operations Office, U.S. Department of Energy

  Awards: DE-AC07-05ID145142, DE-AC02-05CH11231
• DO
  Division of Materials Research

  Awards: DMR 18-47701, 1651668, 18-47701, CER 19-11311, DMR-1651668
• DO
  Division of Civil, Mechanical and Manufacturing Innovation
• BE
  Basic Energy Sciences

  Awards: DE-AC02, AC02-05CH11231, DE-AC02-05CH11231, KC23MP, -AC02-05CH11231
• LD
  Laboratory Directed Research and Development

  Awards: DE-AC07-05ID145142, DE-AC02-05CH11231
• HE
  H2020 European Research Council