Automation of Rietveld refinement through machine learning

Journal article

Rietveld refinement is a widely used technique for determining crystal structures from powder X‐ray diffraction data. Despite its broad applicability, the refinement process often requires substantial manual effort and expert knowledge, which limits the pace of materials research. Here, we introduce a methodology based on convolutional neural networks that enables automated Rietveld refinement. A systematically generated training dataset, which incorporates diverse structural and profile parameters, allows the network to capture complex pattern–structure relationships effectively. A refined crystal structure is directly extracted from the experimental powder X‐ray diffraction pattern in a single inference step. The approach is validated using benchmark datasets of CeO2, Tb2BaCoO5 and PbSO4, achieving reliability factors comparable to those obtained from conventional methods. This work establishes a generalizable methodology by providing valuable insights into the development of autonomous diffraction analysis, with the potential to accelerate materials discovery and characterization.

Authors: Mun, SJ; Nam, Y; Choi, S

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: International Union of Crystallography
• Journal: Journal of Applied Crystallography
• Volume: 59
• Issue: 2
• Publication date: 2026-03-27
• Acceptance date: 2026-02-12
• DOI: 10.1107/s1600576726001494
• EISSN: 1600-5767
• ISSN: 0021-8898
• Language: English
• Keywords: deep learning; machine learning; automatic Rietveld refinements; convolutional neural networks; powder X‐ray diffraction