Scalable Crystal Structure Relaxation Using an Iteration-Free Deep Generative Model with Uncertainty Quantification

TL;DR

DeepRelax is a fast, iteration-free deep generative model for crystal structure relaxation that predicts equilibrium structures directly, enabling scalable and reliable materials discovery with integrated uncertainty quantification.

Contribution

This work introduces DeepRelax, a novel deep generative model that performs rapid, iteration-free crystal relaxation, significantly improving scalability over traditional methods.

Findings

DeepRelax predicts relaxed structures with high accuracy across diverse datasets.

It operates at millisecond speed per structure, enabling large-scale screening.

Uncertainty quantification enhances trustworthiness of predictions.

Abstract

In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and complex twisted structures has challenged traditional computational methods, both ab initio and machine-learning-based, due to their computationally intensive iterative processes. To address these scalability issues, here we introduce DeepRelax, a deep generative model capable of performing geometric crystal structure relaxation rapidly and without iterations. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. We demonstrate DeepRelax's reliability and robustness by applying it to five diverse databases, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high accuracy and efficiency, validated by density functional theory calculations. Finally, we enhance its trustworthiness by integrating uncertainty quantification. This work significantly accelerates computational workflows, offering a robust and trustworthy machine-learning method for material discovery and advancing the application of AI for science. Code for DeepRelax is available at https://github.com/Shen-Group/DeepRelax.