Graph deep learning accelerated efficient crystal structure search and feature extraction

TL;DR

This paper introduces a machine learning framework that accelerates crystal structure search and feature extraction, significantly reducing computational costs while maintaining accuracy, and discovering new stable structures.

Contribution

The authors develop a novel ML-based framework combining symmetry-based optimization and feature attribution, enabling faster and more accurate materials design processes.

Findings

Identified 28 new stable structures in a B-C-N system.

SCCOP is about 10 times faster than traditional methods.

The framework reveals key structural features influencing energy and bandgap.

Abstract

Structural search and feature extraction are a central subject in modern materials design, the efficiency of which is currently limited, but can be potentially boosted by machine learning (ML). Here, we develop an ML-based prediction-analysis framework, which includes a symmetry-based combinatorial crystal optimization program (SCCOP) and a feature additive attribution model, to significantly reduce computational costs and to extract property-related structural features. Our method is highly accurate and predictive, and extracts structural features from desired structures to guide materials design. As a case study, we apply our new approach to a two-dimensional B-C-N system, which identifies 28 previously undiscovered stable structures out of 82 compositions; our analysis further establishes the structural features that contribute most to energy and bandgap. Compared to conventional approaches, SCCOP is about 10 times faster while maintaining a comparable accuracy. Our new framework is generally applicable to all types of systems for precise and efficient structural search, providing new insights into the relationship between ML-extracted structural features and physical properties.