.png){kind=icon}
Return
Crystal structure prediction based on diffusion model and graph network optimization
.png){kind=icon}
PRE
AI
DOI：doi:10.1088/2515-7639/adeaed.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurately and quickly predicting the crystal structures of unknown materials can significantly accelerate the discovery of new materials. However, stable crystal structures only exist at the global minimum of formation energy, making optimization based on density functional theory calculations or graph neural networks (GNNs) surrogate models time-consuming due to the extensive search space. In this work, we propose a crystal structure prediction method called DiffOA, which combines a diffusion model with an optimization algorithm based on GNNs. By generating atomic coordinates through a diffusion process and minimizing the formation energy through an optimization process, DiffOA effectively reduces the searching space required for crystal structure prediction while respecting both the minimum energy principle and the symmetry of crystal structures. We evaluated our method on the prediction of crystal structures of 29 compounds and found that DiffOA achieves a speed three times faster while maintaining comparable performance to GNNs-based optimization method. The high efficiency and accuracy of DiffOA may open a new path for data-driven materials discovery.
Keywords:
crystal structure prediction
diffusion model
graph neural networks
optimization algorithm
materials discovery
Journal
J
IF:
4.3
Papers:
100
Citations:
2.0K
Organization
No organization information available
Cited Papers
ShareSaveGlobal space-group optimization problem: Finding the stablest crystal structure without constraints.png)
PHYSICAL REVIEW B
PHYSICAL REVIEW BIF3.7
PREAI
ShareSaveShareSaveShareSaveMAGUS: machine learning and graph theory assisted universal structure searcherNATIONAL SCIENCE REVIEW
OAAI
NATIONAL SCIENCE REVIEWIF17.1
OAAIShareSaveCommentary: The Materials Project: A materials genome approach to accelerating materials innovationAPL MATERIALS
OAAI
APL MATERIALSIF4.5
OAAIShareSaveShareSave
View more