Machine learning potentials (MLPs) have become an indispensable tool in large-scale atomistic simulations because of their ability to reproduce ab initio potential energy surfaces (PESs) very accurately at a fraction of computational cost. For computational efficiency, the training data for most MLPs today are computed using relatively cheap density functional theory (DFT) methods such as the Perdew-Burke-Ernzerhof (PBE) generalized gradient approximation (GGA) functional. Meta-GGAs such as the recently developed strongly constrained and appropriately normed (SCAN) functional have been shown to yield significantly improved descriptions of atomic interactions for diversely bonded systems, but their higher computational cost remains an impediment to their use in MLP development. In this work, we outline a data-efficient multi-fidelity approach to constructing Materials 3-body Graph Network (M3GNet) interatomic potentials that integrate different levels of theory within a single model. Using silicon and water as examples, we show that a multi-fidelity M3GNet model trained on a combined dataset of low-fidelity GGA calculations with 10% of high-fidelity SCAN calculations can achieve accuracies comparable to a single-fidelity M3GNet model trained on a dataset comprising 8x the number of SCAN calculations. This work paves the way for the development of high-fidelity MLPs in a cost-effective manner by leveraging existing low-fidelity datasets.
Multi-fidelity learning for interatomic potentials: Low-level forces and high-level energies are all you need
Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室);Brigham Young University(杨百翰大学);Max Planck Institute for Polymer Research(马克斯·普朗克聚合物研究所);Nvidia Corporation(英伟达公司);Oak Ridge National Laboratory(橡树岭国家实验室)
E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
Harvard University(哈佛大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Robert Bosch Research and Technology Center(罗伯特·博世研究与技术中心);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Massachusetts Institute of Technology(麻省理工学院)
High-performance training and inference for deep equivariant interatomic potentials
John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·A·保罗森工程与应用科学学院);Center for Computational Science and Engineering, Massachusetts Institute of Technology(麻省理工学院计算科学与工程中心);Department of Materials Science and Engineering, Massachusetts Institute of Technology(麻省理工学院材料科学与工程系);Center for the Environment, Harvard University(哈佛大学环境中心);Research Laboratory of Electronics, Massachusetts Institute of Technology(麻省理工学院电子研究实验室);Sandia National Laboratories(桑尼亚国家实验室);Robert Bosch LLC Research and Technology Center(罗伯特·博世 LLC 研究与技术中心);Mirian Technologies Inc.(Mirian 技术公司)
Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
由于计算成本高,使用{ \it ab initio}分子动力学(AIMD)在室温下精确模拟锂离子在电池材料中的扩散过程一直是一个挑战。近年来,由于基于机器学习的原子间势的进步,这种情况发生了巨大变化。在这里,我们实现了深电位发生器计划,以\textit{automatically}产生LiGePS型固态电解质材料的原子间相互作用势。这增加了我们模拟这些材料的能力,在不牺牲{ \it ab initio}精度的情况下,提高了几个数量级。重要的技术方面,如统计误差和尺寸效应进行了仔细研究。我们进一步建立了一个可靠的协议,在实验条件下准确计算锂离子扩散过程,通过调查重要的技术方面,如统计误差和尺寸效应。这样的协议和自动化工作流程使我们能够以更高的效率筛选材料的相关属性。通过使用这里开发的协议和自动化的工作流程,我们得到的扩散系数数据和锂离子扩散的活化能,以及同意与实验。本文的工作为进一步研究锂离子扩散机理和优化固态电解质材料的锂离子导电性能奠定了基础。
Distilling latent electrostatics from foundation machine learning interatomic potentials
Department of Chemistry, UC Berkeley(加州大学伯克利分校化学系);Bakar Institute of Digital Materials for the Planet, UC Berkeley(伯克利大学数字材料研究所);Chemical Sciences Division, Lawrence Berkeley National Laboratory(伯克利国家实验室化学科学部)
Machine-Learned Interatomic Potentials for Structural and Defect Properties of YBa$_2$Cu$_3$O$_{7-δ}$
Politecnico di Torino(都灵理工大学);Istituto Nazionale di Fisica Nucleare, Sezione di Torino(意大利国家核物理研究所都灵分部);Lancaster University(兰卡斯特大学);University of Helsinki(赫尔辛基大学);Eni S.p.A.(埃尼集团);United Kingdom Atomic Energy Authority(英国原子能管理局)
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)
Mixture of Experts Framework in Machine Learning Interatomic Potentials for Atomistic Simulations
Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA(材料科学与工程系,麻省理工学院,剑桥,马萨诸塞州,美国);John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA(约翰·A·波尔森工程与应用科学学院,哈佛大学,剑桥,马萨诸塞州,美国);Robert Bosch LLC Research and Technology Center, Watertown, MA, USA(罗伯特·博世 LLC 研究与技术中心,沃特敦,马萨诸塞州,美国)
dpti: An Automated Thermodynamic Integration Workflow for Phase Diagram Calculations with Machine Learning Interatomic Potentials
University of Alabama at Birmingham(阿拉巴马大学伯明翰分校);Princeton University(普林斯顿大学);University of Science and Technology of China(中国科学技术大学);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);Suzhou Big Data & AI Research and Engineering Center(苏州大数据与人工智能研究与工程中心);AI for Science Institute(科学智能研究所);DP Technology(深势科技);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)
Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
Princeton University(普林斯顿大学);Institute of Applied Physics and Computational Mathematics(应用物理与计算数学研究所);CAEP Software Center for High Performance Numerical Simulation(中国工程物理研究院高性能数值模拟软件中心);Peking University(北京大学)
Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport
University of Pennsylvania(宾夕法尼亚大学);Massachusetts Institute of Technology(麻省理工学院)