Phonons play a critical role in determining various material properties, but conventional methods for phonon calculations are computationally intensive, limiting their broad applicability. In this study, we present an approach to accelerate high-throughput harmonic phonon calculations using machine learning universal potentials. We train a state-of-the-art machine learning interatomic potential, based on multi-atomic cluster expansion (MACE), on a comprehensive dataset of 2,738 crystal structures with 77 elements, totaling 15,670 supercell structures, computed using high-fidelity density functional theory (DFT) calculations. Our approach significantly reduces the number of required supercells for phonon calculations while maintaining high accuracy in predicting harmonic phonon properties across diverse materials. The trained model is validated against phonon calculations for a held-out subset of 384 materials, achieving a mean absolute error (MAE) of 0.18 THz for vibrational frequencies from full phonon dispersions, 2.19 meV/atom for Helmholtz vibrational free energies at 300K, as well as a classification accuracy of 86.2% for dynamical stability of materials. A thermodynamic analysis of polymorphic stability in 126 systems demonstrates good agreement with DFT results at 300 K and 1000 K. In addition, the diverse and extensive high-quality DFT dataset curated in this study serves as a valuable resource for researchers to train and improve other machine learning interatomic potential models.
Accelerating Phonon Thermal Conductivity Prediction by an Order of Magnitude Through Machine Learning-Assisted Extraction of Anharmonic Force Constants
Accelerating discovery of infrared nonlinear optical materials with large shift current via high-throughput screening
Soochow University(苏州大学);AI for Science Institute(人工智能科学研究院);Research Institute for Intelligent Wearable Systems, The Hong Kong Polytechnic University(香港理工大学智能穿戴系统研究所);Department of Mechanical Engineering, National University of Singapore(新加坡国立大学机械工程系);Suzhou Institute for Advanced Research, University of Science and Technology of China(中国科学技术大学苏州高等研究院);School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China(中国科学技术大学生命科学与医学学院生物医学工程系)
High-Throughput Discovery of Chiral Carbon-Boron Semimetals with Weyl Topology and Phonon-Mediated Superconductivity
University of Science and Technology of China(中国科学技术大学);Wuhan Institute of Technology(武汉工程大学);Hefei University of Technology(合肥工业大学);Hanhai Lingchao Intelligent Computing (Shanghai) Technology Services Co., Ltd.(瀚海凌潮智能计算(上海)科技有限公司)
Electron-phonon-averaged approximation for first-principles computations of electron relaxation times and transport properties in semiconductor materials
High-throughput computational framework for lattice dynamics and thermal transport including high-order anharmonicity: an application to cubic and tetragonal inorganic compounds
Northwestern University(西北大学);Portland State University(波特兰州立大学)
Princeton University(普林斯顿大学);Zhejiang University(浙江大学);Donostia International Physics Center(圣塞巴斯蒂安国际物理中心);Max Planck Institute for Chemical Physics of Solids(马克斯·普朗克固体化学物理研究所);Chongqing University(重庆大学);University of the Basque Country UPV/EHU(巴斯克国立大学);Peking University(北京大学);IKERBASQUE, Basque Foundation for Science(伊克尔巴斯克,巴斯克科学基金会)
Accelerating dynamic simulations of photoexcited materials and their evolution by electron-informed machine learning
Beijing National Laboratory for Condensed Matter Physics and Institute of Physics, Chinese Academy of Sciences(中国科学院物理研究所凝聚态物理国家实验室);School of Physical Sciences, University of Chinese Academy of Sciences(中国科学院大学物理科学学院);Songshan Lake Materials Laboratory(松山湖材料实验室)
Database and deep-learning scalability of anharmonic phonon properties by automated brute-force first-principles calculations
The University of Tokyo(东京大学);The Institute of Statistical Mathematics, Research Organization of Information and Systems(信息系统研究组织统计数学研究所);Zhejiang University(浙江大学);Eurecat, Technology Centre of Catalonia(加泰罗尼亚技术中心 Eurecat);University of Notre Dame(圣母大学);National Institute for Materials Science(物质材料研究机构);Nanyang Technological University(南洋理工大学);Cornell University(康奈尔大学);University of South Carolina(南卡罗来纳大学);Purdue University(普渡大学);The Graduate University for Advanced Studies, SOKENDAI(日本高等研究院 SOKENDAI);Oak Ridge National Laboratory(橡树岭国家实验室);Carnegie Mellon University(卡内基梅隆大学);Agency for Science Technology and Research(新加坡科技研究局);National University of Singapore(新加坡国立大学);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心)
High-throughput screening of spin Hall conductivity in 2D materials
Institute of Materials Science, Technology University of Darmstadt(达姆施塔特工业大学材料科学研究所);Department of Physics, Southern University of Science and Technology(南方科技大学物理系);Department of Physics and CSMB, Humboldt University of Berlin(柏林洪堡大学物理系与跨学科分子生物中心)
The HTC-Claw: Automating Discovery through High-Throughput Computational Campaigns
State Key Laboratory of Metal Matrix Composites, School of Materials Science and Engineering, Shanghai Jiao Tong University(上海交通大学材料科学与工程学院金属基复合材料国家重点实验室)
Accelerating Discovery of Vacancy Ordered 18-Valence Electron Half-Heusler Compounds: A Synergistic Approach of Machine Learning and Density Functional Theory
KAN-Enhanced Contrastive Learning Accelerating Crystal Structure Identification from XRD Patterns
Materials Genome Institute, Shanghai University(上海大学材料基因组研究所);The University of Sydney(悉尼大学);Shanghai University(上海大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))