Identifying Crystal Structures Beyond Known Prototypes from X-ray Powder Diffraction Spectra

TL;DR

This paper introduces a machine learning-based method to identify novel crystal structures from powder diffraction data without relying on existing prototype databases, enabling discovery of new atomic arrangements.

Contribution

The authors develop a novel scheme combining ML, symmetry enumeration, and DFT validation to find previously unobserved crystal structures from XRD spectra.

Findings

Successfully identified stable structures from unknown XRD spectra.

Discovered at least two new crystal prototypes not in prior datasets.

Method does not depend on existing prototype databases.

Abstract

The large amount of powder diffraction data for which the corresponding crystal structures have not yet been identified suggests the existence of numerous undiscovered, physically relevant crystal structure prototypes. In this paper, we present a scheme to resolve powder diffraction data into crystal structures with precise atomic coordinates by screening the space of all possible atomic arrangements, i.e., structural prototypes, including those not previously observed, using a pre-trained machine learning (ML) model. This involves (i) enumerating all possible symmetry-confined ways in which a given composition can be accommodated in a given spacegroup, (ii) ranking the element-assigned prototype representations using energies predicted using the Wren ML model [Sci.Adv.8, eabn4117 (2022)], (iii) assigning and perturbing atoms along the degree of freedom allowed by the Wyckoff positions to match the experimental diffraction data (iv) validating the thermodynamic stability of the material using density-functional theory (DFT). An advantage of the presented method is that it does not rely on a database of previously observed prototypes and is, therefore capable of finding crystal structures with entirely new symmetric arrangements of atoms. We demonstrate the workflow on unidentified XRD spectra from the ICDD database and identify a number of stable structures, where a majority turns out to be derivable from known prototypes. However, at least two are found not to be part of our prior structural data sets.