Experimental Powder X-ray Diffraction Crystal Structure Determination with RealPXRD-Solver

TL;DR

RealPXRD-Solver is a generative model that significantly improves crystal structure determination from powder X-ray diffraction data, achieving high accuracy on theoretical and experimental datasets and solving previously unreported structures.

Contribution

The paper introduces RealPXRD-Solver, a novel generative model trained on extensive theoretical data with augmentations, enabling accurate lattice-conditioned and lattice-free inference from powder X-ray diffraction data.

Findings

Achieves 98.3% Top-20 match rate on theoretical benchmark.

Attains Top-1/Top-20 accuracies of 77.9%/91.9% (CNRS) and 78.8%/92.9% (RRUFF).

Solved 39 previously unreported diffraction entries.

Abstract

Determining crystal structures from experimental powder X-ray diffraction data remains challenging because peak overlap, preferred orientation, and impurity phases obscure atomic arrangements. We present RealPXRD-Solver, a generative model trained on 6,250,238 theoretical structures with experiment-mimicking augmentations and a universal encoder of d-spacing--intensity fingerprints, enabling both lattice-conditioned and lattice-free inference. RealPXRD-Solver reaches a 98.3% Top-20 match rate on a 10,000-structure theoretical benchmark and achieves Top-1/Top-20 accuracies of 77.9%/91.9% on CNRS and 78.8%/92.9% on RRUFF experimental datasets, and it solved 39 previously unreported Powder Diffraction File entries.