CrystalFlow: A Flow-Based Generative Model for Crystalline Materials

作     者：Luo, Xiaoshan Wang, Zhenyu Lv, Jian Wang, Lei Wang, Yanchao Ma, Yanming 

作者机构：Key Laboratory of Material Simulation Methods and Software Ministry of Education College of Physics Jilin University Changchun130012 China State Key Laboratory of Superhard Materials College of Physics Jilin University Changchun130012 China International Center of Future Science Jilin University Changchun130012 China Beijing National Laboratory for Condensed Matter Physics Institute of Physics Chinese Academy of Sciences Beijing100190 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Crystalline materials 

摘      要：Deep learning-based generative models have emerged as powerful tools for modeling complex data distributions and generating high-fidelity samples, offering a transformative approach to efficiently explore the configuration space of crystalline materials. In this work, we present CrystalFlow, a flow-based generative model specifically developed for the generation of crystalline materials. CrystalFlow constructs Continuous Normalizing Flows to model lattice parameters, atomic coordinates, and/or atom types, which are trained using Conditional Flow Matching techniques. Through an appropriate choice of data representation and the integration of a graph-based equivariant neural network, the model effectively captures the fundamental symmetries of crystalline materials, which ensures data-efficient learning and enables high-quality sampling. Our experiments demonstrate that CrystalFlow achieves state-of-the-art performance across standard generation benchmarks, and exhibits versatile conditional generation capabilities including producing structures optimized for specific external pressures or desired material properties. These features highlight the model’s potential to address realistic crystal structure prediction challenges, offering a robust and efficient framework for advancing data-driven research in condensed matter physics and material science. Copyright © 2024, The Authors. All rights reserved.