Crystal Structure Determination from Powder Diffraction Patterns with Generative Machine Learning

• DOI: 10.1021/jacs.4c10244
• Publication Date: 2024-09-19T16:33:23Z
• Authors: Eric A. Riesel; Tsach Mackey; Hamed Nilforoshan; Minkai Xu; Catherine K. Badding; Alison B. Altman; Jure Leskovec; Danna E. Freedman
• Keywords: Powder Diffraction; Crystal (programming language)

Powder X-ray diffraction (PXRD) is a cornerstone technique in materials characterization. However, complete structure determination from PXRD patterns alone remains time-consuming and often intractable, especially for novel materials. Current machine learning (ML) approaches to analysis predict only subset of the total information that comprises crystal structure. We developed pioneering generative ML model designed solve structures real-world experimental data. In addition strong performance on simulated patterns, we demonstrate full solutions over large set patterns. Benchmarking our model, predicted 134 RRUFF database thousands Materials Project which achieves state-of-the-art 42 67% match rate, respectively. Further, applied determine unreported such as NaCu