机器学习原子间势在材料跨尺度计算模拟中的最新进展
Recent advances in machine learning interatomic potentials for cross-scale computational simulation of materials
冉念 1殷亮 2邱吴劼 3刘建军2
作者信息
- 1. State Key Laboratory of High Performance Ceramics and Superfine Microstructure,Shanghai Institute of Ceramics,Chinese Academy of Sciences,Shanghai 200050,China;Center of Materials Science and Optoelectronics Engineering,University of Chinese Academy of Sciences,Beijing 100049,China
- 2. State Key Laboratory of High Performance Ceramics and Superfine Microstructure,Shanghai Institute of Ceramics,Chinese Academy of Sciences,Shanghai 200050,China;Center of Materials Science and Optoelectronics Engineering,University of Chinese Academy of Sciences,Beijing 100049,China;School of Chemistry and Materials Science,Hangzhou Institute for Advanced Study,University of Chinese Academy of Sciences,Hangzhou 310024,China
- 3. State Key Laboratory of High Performance Ceramics and Superfine Microstructure,Shanghai Institute of Ceramics,Chinese Academy of Sciences,Shanghai 200050,China;Center of Materials Science and Optoelectronics Engineering,University of Chinese Academy of Sciences,Beijing 100049,China;School of Mathematics,Physics and Statistics,Shanghai Polytechnic University,Shanghai 201209,China
- 折叠
摘要
近年来,机器学习原子势(ML-IP)因其兼顾高精度和高效率的优势,在材料科学、化学、生物学等领域的大尺度原子模拟研究中引起了广泛关注.本文聚焦于ML-IP在材料跨尺度计算模型中的应用,全面介绍了ML-IP的结构采样、结构描述符和拟合方法.这些方法使ML-IP能够以高精度和高效率模拟分子和晶体的动力学和热力学特性.跨学科研究领域中更高效、先进的技术在开拓覆盖不同时间和空间尺度的广泛应用方面发挥着重要作用.因此,ML-IP方法为未来的研究和创新铺平了道路,为多个领域带来了革命性的机会.
Abstract
In recent years,machine learning interatomic potentials(ML-IPs)have attracted extensive attention in ma-terials science,chemistry,biology,and various other fields,particularly for achieving higher precision and efficiency in conducting large-scale atomic simulations.This review,si-tuated in the ML-IP applications in cross-scale computational models of materials,offers a comprehensive overview of structure sampling,structure descriptors,and fitting meth-odologies for ML-IPs.These methodologies empower ML-IPs to depict the dynamics and thermodynamics of molecules and crystals with remarkable accuracy and efficiency.More effi-cient and advanced techniques from interdisciplinary research field play an important role in opening a wide spectrum of applications spanning diverse temporal and spatial dimen-sions.Therefore,ML-IP method renders the stage for future research and innovation promising revolutionary opportu-nities across multiple domains.
关键词
machine learning interatomic potential/cross-scale computational simulation/structure sampling/encoding struc-ture/fitting methodKey words
machine learning interatomic potential/cross-scale computational simulation/structure sampling/encoding struc-ture/fitting method引用本文复制引用
基金项目
国家重点研发计划(2022YFB3807200)
Shanghai Explorer Program(Batch I)(23TS1401500)
国家自然科学基金(22133005)
中国博士后科学基金(2022M723276)
中国博士后科学基金(GZB20230793)
Shanghai Sailing Program(23YF1454900)
Shanghai Postdoctoral Excellence Program(2022660)
出版年
2024
NETL
NSTL
万方数据