AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning

TL;DR

AlphaCrystal-II addresses the challenge of predicting crystal structures from composition by predicting an inter-atomic distance matrix with a deep residual network and reconstructing 3D structures via a distance-matrix-based pipeline. The method leverages abundant inter-atomic patterns from known crystal structures and integrates a DMCrystal genetic algorithm and M3GNet relaxation to identify stable configurations. On Materials Project data, AlphaCrystal-II demonstrates competitive or superior performance to baseline CSP methods, including GNOA, across diverse compositions, and shows strong distance-matrix prediction and reconstruction capabilities. This data-driven, knowledge-guided approach suggests a scalable path toward large-scale CSP for materials discovery.

Abstract

Computational prediction of stable crystal structures has a profound impact on the large-scale discovery of novel functional materials. However, predicting the crystal structure solely from a material's composition or formula is a promising yet challenging task, as traditional ab initio crystal structure prediction (CSP) methods rely on time-consuming global searches and first-principles free energy calculations. Inspired by the recent success of deep learning approaches in protein structure prediction, which utilize pairwise amino acid interactions to describe 3D structures, we present AlphaCrystal-II, a novel knowledge-based solution that exploits the abundant inter-atomic interaction patterns found in existing known crystal structures. AlphaCrystal-II predicts the atomic distance matrix of a target crystal material and employs this matrix to reconstruct its 3D crystal structure. By leveraging the wealth of inter-atomic relationships of known crystal structures, our approach demonstrates remarkable effectiveness and reliability in structure prediction through comprehensive experiments. This work highlights the potential of data-driven methods in accelerating the discovery and design of new materials with tailored properties.

Figures (7)

• Figure 1: The AlphaCrystal-II framework for distance matrix-based crystal structure prediction. First, material compositions are encoded into feature matrices according to their atom features, which are used to train the deep neural network for predicting distance matrices. Next, the crystal structures are reconstructed by DMCCrystal GA along with predicted unit cell information. The resulting candidate structures are then relaxed by the M3GNet model. For multiple candidate structures, the top K structures are selected based on their predicted formation energies determined by M3GNet.
• Figure 2: Deep neural network model for distance matrix prediction.
• Figure 3: Overall atomic distance distribution of Mp_12 dataset. The x-axis represents the atomic distance and the y-axis represents the corresponding ratios. The most atomic distances are in the range of 2.33-4.67, accounting for more than 25% and there are just a few distances more than 14.
• Figure 4: Comparison of formation energies of predicted structures by GNOA and AlphaCrystal-II.
• Figure 5: Examples of predicted crystal structures by AlphaCrystal-II. (a) the ground truth structure of Zr$_{4}$Al$_{3}$; (b) the predicted structure of Zr$_{4}$Al$_{3}$ by GNOA; (c) the predicted structure of Zr$_{4}$Al$_{3}$ by AlphaCrystal-II; (d) the ground truth structure of ScAl; (e) the predicted structure of ScAl by GNOA; (f) the predicted structure of ScAl by AlphaCrystal-II; (g) the ground truth structure of EuNbNO$_{2}$; (h) the predicted structure of EuNbNO$_{2}$ by GNOA; (i) the predicted structure of EuNbNO$_{2}$ by AlphaCrystal-II;