Fourier Neural Operators for Composition-Driven Crystal Structure Discovery
Abstract
Crystalline materials discovery is essential for energy, electronics, and catalysis, but the vast chemical and structural space makes exhaustive screening infeasible. Existing voxel-based methods are limited by the local receptive fields of three-dimensional convolutional neural networks and the posterior collapse of high-dimensional variational autoencoders. Here, we develop a Fourier Neural Operator (FNO)-based crystal-field solver that maps a prescribed chemical formula and lattice parameters to periodic number-density and electron-density fields. By operating on global Fourier modes, the solver captures long-range correlations in periodic crystal fields beyond conventional local convolutions. Building on this solver, we construct a coupled generation-solving framework in which a conditional variational autoencoder generates diverse candidate lattice parameters in a low-dimensional basis-coefficient space, followed by density-field prediction and atomic reconstruction through peak detection, position optimization, and weight optimization. The reconstructed structures are further screened using voxel-level filtering, machine-learning interatomic-potential relaxation, and first-principle calculations. The framework generates novel structures across 104 chemical formulas with competitive reconstruction accuracy, demonstrating high generative diversity and structural validity. By extending Fourier neural operators to periodic crystal fields and coupling them with composition-conditioned lattice generation, our approach provides a scalable route to crystal structure discovery from prescribed chemical compositions.
Related
- Structure-preserving Fourier Neural Operators for Long-time Cahn-Hilliard Dynamics under Coarse Temporal Supervision
- Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening
- Euclidean Fourier Neural Operators
- Learning Metamaterial Eigenmodes with Wavelet-Encoded Fourier Neural Operators
- When do machine-learning potentials need a configuration-dependent kernel? Learning long-range interactions with Fourier neural operators
BibTeX
@misc{yu2026fourier,
title = {{Fourier Neural Operators for Composition-Driven Crystal Structure Discovery}},
author = {Zhijie Yu and Jingyu Li and Yang Huang and Jingrun Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00900},
eprint = {2609.00900},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00900},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Fourier Neural Operators for Composition-Driven Crystal Structure Discovery
AU - Zhijie Yu
AU - Jingyu Li
AU - Yang Huang
AU - Jingrun Chen
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00900
UR - https://arxiv.org/abs/2609.00900
AB - Crystalline materials discovery is essential for energy, electronics, and catalysis, but the vast chemical and structural space makes exhaustive screening infeasible. Existing voxel-based methods are limited by the local receptive fields of three-dimensional convolutional neural networks and the posterior collapse of high-dimensional variational autoencoders. Here, we develop a Fourier Neural Operator (FNO)-based crystal-field solver that maps a prescribed chemical formula and lattice parameters to periodic number-density and electron-density fields. By operating on global Fourier modes, the solver captures long-range correlations in periodic crystal fields beyond conventional local convolutions. Building on this solver, we construct a coupled generation-solving framework in which a conditional variational autoencoder generates diverse candidate lattice parameters in a low-dimensional basis-coefficient space, followed by density-field prediction and atomic reconstruction through peak detection, position optimization, and weight optimization. The reconstructed structures are further screened using voxel-level filtering, machine-learning interatomic-potential relaxation, and first-principle calculations. The framework generates novel structures across 104 chemical formulas with competitive reconstruction accuracy, demonstrating high generative diversity and structural validity. By extending Fourier neural operators to periodic crystal fields and coupling them with composition-conditioned lattice generation, our approach provides a scalable route to crystal structure discovery from prescribed chemical compositions.
ER -