机器学习(ML)方法能够以接近量子力学的精度开展大规模原子模拟。随着这些方法日益普及,人们需要对其进行谨慎验证,尤其是对于物理无关模型——即从参考数据中提取原子相互作用本质的势函数。在此,我们综述了 ML 势及其在原子尺度材料建模中验证的基本原则。我们讨论了基于数值性能定义误差指标以及物理引导验证的最佳实践。我们给出了具体建议,希望这些建议能对更广泛的群体有所帮助,包括那些打算将 ML 势作为材料“现成”工具使用的研究人员。
英文摘要:
Machine learning (ML) approaches enable large-scale atomistic simulations with near-quantum-mechanical accuracy. With the growing availability of these methods there arises a need for careful validation, particularly for physically agnostic models - that is, for potentials which extract the nature of atomic interactions from reference data. Here, we review the basic principles behind ML potentials and their validation for atomic-scale materials modeling. We discuss best practice in defining error metrics based on numerical performance as well as physically guided validation. We give specific recommendations that we hope will be useful for the wider community, including those researchers who intend to use ML potentials for materials "off the shelf".
Revealing Hydroxide Ion Transport Mechanisms in Commercial Anion-Exchange Membranes at Nano-Scale from Machine-learned Interatomic Potential Simulations
Technische Universität Ilmenau(伊尔梅瑙工业大学);Fraunhofer-Institut für Keramische Technologien und Systeme IKTS(弗劳恩霍夫陶瓷技术与系统研究所)
Overcoming sampling limitations using machine-learned interatomic potentials: the case of water-in-salt electrolytes
Sorbonne Université(索邦大学);Muséum National d’Histoire Naturelle(国家自然历史博物馆);Physicochimie des Électrolytes et Nanosystèmes Interfaciaux(电解质与界面纳米系统物理化学);Laboratoire de Physique de L’École Normale Supérieure de Paris(巴黎高等师范学院物理实验室)
本文评估了不同MACE势在模拟21m水盐电解质中的性能,展示了 surrogate 模型如何克服 ab initio 分子动力学的采样限制,并证明了微调基础模型在数据效率和捕捉难采样构型方面的优势。
False Metallization in Short-Ranged Machine Learned Interatomic Potentials
University of Cambridge(剑桥大学);BASF SE, Group Research(巴斯夫股份公司集团研究);BASF Chemicals India Pvt. Ltd.(巴斯夫印度化工有限公司);California Institute of Technology(加州理工学院)
Electrostatic Phenomenology Benchmarks for Machine-Learned Interatomic Potentials in Electrochemistry: Beyond the Energy-Force Metric
Fritz-Haber-Institut der Max-Planck-Gesellschaft(马克斯·普朗克学会弗里茨·哈伯研究所);Department of Chemistry and Biochemistry, University of South Carolina(南卡罗来纳大学化学与生物化学系);Department of Chemical Engineering, University of California, Davis(加州大学戴维斯分校化学工程系);Department of Materials, Imperial College London(帝国理工学院材料系);Department of Chemistry, Imperial College London(帝国理工学院化学系);Department of Materials Science and Engineering, University of Florida(佛罗里达大学材料科学与工程系);Department of Chemistry, Korea University(高丽大学化学系);Max Planck Institute for Sustainable Materials(马克斯·普朗克可持续材料研究所)
Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials
Institute for Theoretical Chemistry, University of Stuttgart(斯图加特大学理论化学研究所);Institute for Computational Physics, University of Stuttgart(斯图加特大学计算物理研究所)
From Energy-Force Weighting to Primal-Dual Optimization of Machine-Learned Interatomic Potentials
School of Mathematical Sciences, Institute of Natural Sciences and MOE-LSC, Shanghai Jiao Tong University(上海交通大学数学科学学院、自然科学研究院和教育部线性科学中心);Department of Mathematics, National University of Singapore(新加坡国立大学数学系)
Excited-state nonadiabatic dynamics in explicit solvent using machine learned interatomic potentials
Research Platform on Accelerating Photoreaction Discovery (ViRAPID), University of Vienna(维也纳大学加速光反应发现研究平台(ViRAPID));Vienna Doctoral School in Chemistry, University of Vienna(维也纳大学维也纳化学博士学院);Institute of Theoretical Chemistry, Faculty of Chemistry, University of Vienna(维也纳大学化学学院理论化学研究所);Department of Chemistry, Sapienza University of Rome(罗马大学化学系);Wilhelm-Ostwald Institute, University of Leipzig(莱比锡大学威廉·奥斯特瓦尔德研究所)
Knowing when to trust machine-learned interatomic potentials
Department of Chemistry, Mellon College of Science(化学系,梅隆科学学院);Department of Materials Science and Engineering(材料科学与工程系);Ray and Stephanie Lane Computational Biology Department, School of Computer Science(Ray和Stephanie Lane计算生物学部门,计算机科学学院)
Development of machine-learned interatomic potentials to predict structure, transport, and reactivity in platinum-based fuel cells
Rensselaer Polytechnic Institute(伦斯勒理工学院);New Mexico State University(新墨西哥州立大学);National Laboratory of the Rockies(落基山国家实验室);University of South Carolina(南卡罗来纳大学);Sandia National Laboratories(桑迪亚国家实验室)
Benchmarking machine-learned interatomic potentials for molecular infrared spectroscopy
Technical University of Munich(慕尼黑工业大学);Aalto University(阿尔托大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Munich Data Science Institute(慕尼黑数据科学研究所);Department of Chemistry and Material Science, Aalto University(阿尔托大学化学与材料科学系)
Comparing the latent features of universal machine-learning interatomic potentials
Laboratory of Computational Science and Modeling(计算科学与建模实验室);Department of Energy Conversion and Storage(能源转换与存储部门);Technical University of Denmark(丹麦技术大学)
Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, Chinese Academy of Sciences(中国科学院数学与系统科学研究院计算数学与科学工程计算研究所);Institute of Applied Physics and Computational Mathematics(应用物理与计算数学研究所);College of Engineering, Peking University(北京大学工学院)
Systematic Fine-Tuning of MACE Interatomic Potentials for Catalysis
University of South Carolina(南卡罗来纳大学);National Laboratory of the Rockies(落基山国家实验室);Rensselaer Polytechnic Institute(伦斯勒理工学院);University of Cambridge(剑桥大学);Max Planck Institute for Polymer Research(马克斯·普朗克聚合物研究所);University of Toronto(多伦多大学)
Geometric Algebra Meets Cartesian Tensors: Higher-Order Equivariance for Interatomic Potentials
Dept. of Electrical & Computer Eng.(电气与计算机工程系);Texas A&M Univ.(德克萨斯A&M大学);Dept. of Prosthetics & Orthotics(假肢与矫形器系);College of Science & Eng.(科学与工程学院);Ankara Univ.(安卡拉大学);Hamad Bin Khalifa Univ. and Texas A&M Univ. at Qatar(哈马德·本·卡西姆大学和德克萨斯A&M大学(多哈))
HIP: Hessian Interatomic Potentials without derivatives
University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所);Technical University of Denmark(丹麦技术大学);CAPeX Pioneer Center for Accelerating P2X Materials Discovery(CAPeX加速P2X材料发现先锋中心);Acceleration Consortium(加速联盟);Canadian Institute for Advanced Research (CIFAR)(加拿大高等研究院);NVIDIA(英伟达)
Cutting Through the Noise: On-the-fly Outlier Detection for Robust Training of Machine Learning Interatomic Potentials
Cavendish Laboratory, Department of Physics, University of Cambridge(卡文迪许实验室,物理系,剑桥大学);Lennard-Jones Centre, University of Cambridge(兰纳德-琼斯中心,剑桥大学);Yusuf Hamied Department of Chemistry, University of Cambridge(尤苏夫·哈米德化学系,剑桥大学)
Understanding the Density Maximum of Water with Machine Learned Potentials
Temple University(天普大学);Eastern Institute of Technology(宁波东方理工大学);Princeton University(普林斯顿大学);Peking University(北京大学);Institute for Computational Molecular Science, Temple University(天普大学计算分子科学研究所)
Autotuning T-PaiNN: Enabling Data-Efficient GNN Interatomic Potential Development via Classical-to-Quantum Transfer Learning
Materials Science & Engineering, School for the Engineering of Matter, Transport, & Energy, Arizona State University(材料科学与工程系,物质、传输与能源工程学院,亚利桑那州立大学);Chemical Engineering, School for the Engineering of Matter, Transport, & Energy, Arizona State University(化学工程系,物质、传输与能源工程学院,亚利桑那州立大学)