Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints
This work addresses the labor-intensive and costly process of material discovery in materials science, offering an efficient generative design approach with high structural diversity and symmetry.
The paper tackles the challenge of discovering new crystal materials by proposing a deep learning-based generative model that increases generation validity by over 700% compared to a state-of-the-art method and validates 1,869 out of 2,000 generated structures, with 39.6% showing thermodynamic stability.
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.