Deep learning generative model for crystal structure prediction

Abstract

Recent advances in deep learning generative models (GMs) have created high capabilities in accessing and assessing complex high-dimensional data, allowing superior efficiency in navigating vast material configuration space in search of viable structures. Coupling such capabilities with physically significant data to construct trained models for materials discovery is crucial to moving this emerging field forward. Here, we present a universal GM for crystal structure prediction (CSP) via a conditional crystal diffusion variational autoencoder (Cond-CDVAE) approach, which is tailored to allow user-defined material and physical parameters such as composition and pressure. This model is trained on an expansive dataset containing over 670,000 local minimum structures, including a rich spectrum of high-pressure structures, along with ambient-pressure structures in Materials Project database. We demonstrate that the Cond-CDVAE model can generate physically plausible structures with high fidelity under diverse pressure conditions without necessitating local optimization, accurately predicting 59.3% of the 3,547 unseen ambient-pressure experimental structures within 800 structure samplings, with the accuracy rate climbing to 83.2% for structures comprising fewer than 20 atoms per unit cell. These results meet or exceed those achieved via conventional CSP methods based on global optimization. The present findings showcase substantial potential of GMs in the realm of CSP.

References in corpus (21)

• CALYPSO: a method for crystal structure prediction
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Crystal Structure Prediction via Particle Swarm Optimization
• On representing chemical environments
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Superconductivity at 250 K in lanthanum hydride under high pressures
• Evidence for superconductivity above 260 K in lanthanum superhydride at megabar pressures
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Ionic high-pressure form of elemental boron
• Superconductive "sodalite"-like clathrate calcium hydride at high pressures
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• A foundation model for atomistic materials chemistry
• Inverse design of 3d molecular structures with conditional generative neural networks
• An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
• Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures
• A Symmetry-orientated Divide-and-Conquer Method for Crystal Structure Prediction
• MatterGen: a generative model for inorganic materials design
• Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
• Crystal Structure Prediction by Joint Equivariant Diffusion
• Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
• Crystal-GFN: sampling crystals with desirable properties and constraints

Cited by in corpus (9)

• AI-driven inverse design of materials: Past, present and future
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• CrystalFlow: A Flow-Based Generative Model for Crystalline Materials
• Accelerated Inorganic Materials Design with Generative AI Agents
• $\Delta$-model correction of Foundation Model based on the models own understanding
• XtalOpt Version 14: Variable-Composition Crystal Structure Search for Functional Materials Through Pareto Optimization
• Reinforcement Fine-Tuning for Materials Design
• Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks
• LLM-driven discovery for carbon allotropes with bond-network entropy