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

• DOI: 10.1021/acs.chemmater.0c01907
• Publication Date: 2020-05-19T21:13:46Z
• Authors: Anthony Yu-Tung Wang; Ryan J. Murdock; Steven K. Kauwe; Anton O. Oliynyk; Aleksander Gurlo; Jakoah Brgoch; Kristin A. Persson; Taylor D. Sparks
• Keywords: Best practice; Benchmarking; Python; Feature Engineering

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 treatment of data, feature engineering, model training, validation, evaluation comparison, popular repositories data benchmarking sets, architecture sharing, finally publication. In addition, we include interactive Jupyter notebooks with example Python code to demonstrate some concepts, workflows, discussed. Overall, data-driven methods learning workflows considerations are presented a simple way, allowing readers more intelligently guide their research using suggested references, practices, own domain expertise.