1. Grand canonical generative diffusion model for crystalline phases and grain boundaries
- Author
-
Lei, Bo, Chen, Enze, Kwon, Hyuna, Hsu, Tim, Sadigh, Babak, Lordi, Vincenzo, Frolov, Timofey, and Zhou, Fei
- Subjects
Condensed Matter - Materials Science ,Computer Science - Machine Learning - Abstract
The diffusion model has emerged as a powerful tool for generating atomic structures for materials science. This work calls attention to the deficiency of current particle-based diffusion models, which represent atoms as a point cloud, in generating even the simplest ordered crystalline structures. The problem is attributed to particles being trapped in local minima during the score-driven simulated annealing of the diffusion process, similar to the physical process of force-driven simulated annealing. We develop a solution, the grand canonical diffusion model, which adopts an alternative voxel-based representation with continuous rather than fixed number of particles. The method is applied towards generation of several common crystalline phases as well as the technologically important and challenging problem of grain boundary structures.
- Published
- 2024