Machine Learning in X-ray Scattering for Materials Discovery and Characterization

X-ray diffraction (XRD) is an immediate and powerful characterization technique that provides detailed information on the lattice structure and long-range order in crystalline materials. In recent decades, the quality and quantity of available crystal structure data has exploded, in large part due to the advent of online crystal structure databases, increased use of in-situ and operando methodologies, and user-accessible beamlines. The new wealth of data has also spawned an increasing use of machine learning (ML) to either construct high-throughput surrogates of established analysis or extract patterns from large datasets. However, XRD spectroscopy has been for many years solved via Rietveld refinement, while most ML techniques are simply complex statistical evaluation methods that are physics-agnostic. The discrepancy between data analysis and the underlying physics can lead to incorrect conclusions and/or limit the wide-spread adoption of ML techniques. In this review, we bridge the gap between ML and XRD spectroscopy with an introduction designed both for new data scientists and experimentalists interested in problems related to ML-guided spectroscopy analysis. We cover how supervised ML methods are used to predict likely symmetries and phases in pure and mixed samples, including challenges related to experimental artifacts and model interpretation. We also review recent uses of unsupervised methods in the extraction of patterns hidden in high-dimensional data, such as in in-situ and microscopic studies. Finally, we discuss the importance of problem formulation, data transferability, and reporting with recent case studies and give various resources throughout to expedite the learning curve for readers new to XRD or ML. We advocate for greater scrutiny of ML methods, how they are presented in the literature, and how to conduct data-driven research responsibly.