Learning Lattice Parameters from Powder X-Ray Diffraction Data Using Invariants
Abstract
We present a machine learning (ML) method to determine unit cell parameters from powder X-Ray diffraction (XRD) data using a novel invariant lattice representation. In ML, the data representation used can have a substantial impact on the prediction quality. Previous approaches have directly predicted lattice parameters ($a,b,c,α,β,γ$) from XRD inputs. However, these parameters depend strongly on the unit cell reduction or convention used. In this work, we construct an invariant representation of the reciprocal lattice that is independent of primitive cell convention, based on the bispectrum--a descriptor built from spherical harmonic projections of lattice points. The calculation of the lattice bispectrum is differentiable, and we demonstrate how to invert it using gradient-based optimization initialized from a nearest-neighbor lookup. We show that with a fixed ML model architecture, using the lattice bispectrum as the ML target rather than the unit cell parameters leads to more accurate lattice parameter predictions. For example, using the MP-20 dataset, the bispectrum reduces length mean absolute percentage error (MAPE) from 11.08% to 2.43% and angle MAPE from 12.15% to 2.45% compared to direct prediction with the same model architecture. We additionally benchmark our approach against pre-existing XRD to crystal structure models such as Crystalyze and assess its performance on experimental data. Beyond unit cell representation, we anticipate this invariant lattice representation could serve more broadly as a geometry-aware target for other crystallographic machine learning tasks such as structure generation.
Related
- Machine learning magnetic interactions from neutron powder diffraction data
- PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities
- Exploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns
- Scalable machine learning framework for multiphase identification from powder X-ray diffraction
- X2SBench: an open benchmark for evaluating crystal structure determination from powder diffraction
BibTeX
@misc{hofgard2026learning,
title = {{Learning Lattice Parameters from Powder X-Ray Diffraction Data Using Invariants}},
author = {Elyssa Hofgard and Kyucheol Min and Nofit Segal and David W. Mittan-Moreau and Aria Mansouri Tehrani and Vanessa Oklejas and Rafael Gómez-Bombarelli and Jigyasa Nigam and Daniel W. Paley and Aaron S. Brewster and Tess Smidt},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.21829},
eprint = {2607.21829},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.21829},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning Lattice Parameters from Powder X-Ray Diffraction Data Using Invariants
AU - Elyssa Hofgard
AU - Kyucheol Min
AU - Nofit Segal
AU - David W. Mittan-Moreau
AU - Aria Mansouri Tehrani
AU - Vanessa Oklejas
AU - Rafael Gómez-Bombarelli
AU - Jigyasa Nigam
AU - Daniel W. Paley
AU - Aaron S. Brewster
AU - Tess Smidt
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2607.21829
UR - https://arxiv.org/abs/2607.21829
AB - We present a machine learning (ML) method to determine unit cell parameters from powder X-Ray diffraction (XRD) data using a novel invariant lattice representation. In ML, the data representation used can have a substantial impact on the prediction quality. Previous approaches have directly predicted lattice parameters ($a,b,c,α,β,γ$) from XRD inputs. However, these parameters depend strongly on the unit cell reduction or convention used. In this work, we construct an invariant representation of the reciprocal lattice that is independent of primitive cell convention, based on the bispectrum--a descriptor built from spherical harmonic projections of lattice points. The calculation of the lattice bispectrum is differentiable, and we demonstrate how to invert it using gradient-based optimization initialized from a nearest-neighbor lookup. We show that with a fixed ML model architecture, using the lattice bispectrum as the ML target rather than the unit cell parameters leads to more accurate lattice parameter predictions. For example, using the MP-20 dataset, the bispectrum reduces length mean absolute percentage error (MAPE) from 11.08% to 2.43% and angle MAPE from 12.15% to 2.45% compared to direct prediction with the same model architecture. We additionally benchmark our approach against pre-existing XRD to crystal structure models such as Crystalyze and assess its performance on experimental data. Beyond unit cell representation, we anticipate this invariant lattice representation could serve more broadly as a geometry-aware target for other crystallographic machine learning tasks such as structure generation.
ER -