Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints

TL;DR

This paper introduces a physics-guided deep learning model for crystal material design that significantly improves generation validity and structural diversity, validated by DFT calculations and database deposition.

Contribution

The proposed PGCGM model incorporates physics and symmetry constraints, achieving higher validity and diversity in crystal generation compared to previous models.

Findings

Over 700% increase in generation validity over FTCP

45% improvement over CubicGAN in validity

Nearly 40% of generated materials are thermodynamically stable

Abstract

Discovering new materials is a challenging task in materials science crucial to the progress of human society. Conventional approaches based on experiments and simulations are labor-intensive or costly with success heavily depending on experts' heuristic knowledge. Here, we propose a deep learning based Physics Guided Crystal Generative Model (PGCGM) for efficient crystal material design with high structural diversity and symmetry. Our model increases the generation validity by more than 700\% compared to FTCP, one of the latest structure generators and by more than 45\% compared to our previous CubicGAN model. Density Functional Theory (DFT) calculations are used to validate the generated structures with 1,869 materials out of 2,000 are successfully optimized and deposited into the Carolina Materials Database \url{www.carolinamatdb.org}, of which 39.6\% have negative formation energy and 5.3\% have energy-above-hull less than 0.25 eV/atom, indicating their thermodynamic stability and potential synthesizability.