Dyna-Mat: End-to-end benchmarking of foundation machine learning interatomic potentials in finite-temperature ensembles
University College London（伦敦大学学院）；Utrecht University（乌得勒支大学）；National Center for Nuclear Research（国家核研究中心）；Periodic Labs（周期实验室）；Fritz-Haber-Institut der Max-Planck-Gesellschaft（马克斯·普朗克学会弗里茨·哈伯研究所）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）；Ruđer Boškovi’c Institute（鲁杰尔·博什科维奇研究所）；University of Iceland（冰岛大学）
Mikołaj J. Gawkowski, Nongnuch Artrith, Silvia Bonfanti, Abhijeet Sadashiv Gangan, Hendrik H. Heenen, Joseph Kioseoglou, Ivor Lončarić, Hemanadhan Myneni, Janos… 展开作者
Mikołaj J. Gawkowski, Nongnuch Artrith, Silvia Bonfanti, Abhijeet Sadashiv Gangan, Hendrik H. Heenen, Joseph Kioseoglou, Ivor Lončarić, Hemanadhan Myneni, Janosh Riebesell, Mariana Rossi, Matthias Rupp, Jonathan Schmidt, Shubham Sharma, Benjamin X. Shi, Antoni Wadowski, Lukas Hörmann, Venkat Kapil
备注：
40 pages, 16 figures, includes Supporting Information
Foundation machine learning interatomic potentials (MLIPs) are increasingly being used as drop-in replacements for first-principles calculations, enabling simulations of materials at length and time scales that were previously inaccessible. However, due to lack of ground truth data, their accuracy on structural and dynamical observables in finite thermodynamic ensembles is yet to be established. Here, we introduce Dyna-Mat-v1.0, a benchmark dataset of condensed-phase first-principles molecular dynamics trajectories designed to test foundation MLIPs at realistic finite-temperature conditions. Using this dataset, we evaluate 15 foundation MLIPs across four model tiers by comparing both single-point energy and force errors on first-principles configurations and observables generated from MLIP-driven trajectories. We find that "on average" models with lower single-point force errors also yield lower errors for structural and dynamical observables. However, there are individual systems for which low force errors lead to qualitative failures in the predicted structure. Pressure remains poorly described across most models, pointing to limitations in the density functional theory stress labels available in current large-scale training datasets. Finally, we construct an accuracy-cost Pareto frontier to identify the best trade-offs for molecular dynamics with foundation MLIPs, finding that the latest generation of cross-trained models is close to Pareto-optimal according to the accuracy metrics considered here. Overall, Dyna-Mat-v1.0 shows that end-to-end finite-temperature validation is essential for quantifying the predictive behaviour of foundation MLIPs, and provides a simple, scalable route for assessing them beyond static and harmonic benchmarks relevant to materials design.
Benchmarking Machine-Learning Interatomic Potentials for Dynamical Stability in Inorganic Semiconductor Nanocrystals: A CdSe Case Study
BCMaterials, Basque Center for Materials, Applications, and Nanostructures, UPV/EHU（巴斯克材料、应用与纳米结构中心（BCMaterials））；University of the Basque Country (UPV/EHU)（巴斯克大学）；Ikerbasque Basque Foundation for Science（伊克拉巴斯克科学基金会）
Molecular dynamics simulation of the recrystallization of amorphous Si layers: Comprehensive study of the dependence of the recrystallization velocity on the interatomic potential
Ligand-Controlled Phonon Dynamics in CsPbBr3 Nanocrystals Revealed by Machine-Learned Interatomic Potentials
Georgia Institute of Technology（佐治亚理工学院）；Queens College, City University of New York（纽约市立大学皇后学院）；The Graduate Center, City University of New York（纽约市立大学研究生中心）
Evaluating Mechanical Property Prediction across Material Classes using Molecular Dynamics Simulations with Universal Machine-Learned Interatomic Potentials
School of Physics, Chemistry and Earth Sciences, The University of Adelaide（阿德莱德大学物理、化学与地球科学学院）
Comparison of intermediate-range order in GeO$_2$ glass: molecular dynamics using machine-learning interatomic potential vs.\ reverse Monte Carlo fitting to experimental data
Accurate Machine Learning Interatomic Potentials for Polyacene Molecular Crystals: Application to Single Molecule Host-Guest Systems
Max Planck Institute for the Structure and Dynamics of Matter（马克斯·普朗克固体研究和光谱学研究所）；Center for Free-Electron Laser Science（自由电子激光科学中心）；Initiative for Computational Catalysis (ICC)（计算催化倡议）；The Flatiron Institute（平顿研究所）
Development of a magnetic interatomic potential for cubic anti-ferromagnets: the case of NiO
IT4Innovations VŠB - Technical University of Ostrava（IT4创新与卓越中心 俄斯特拉发理工大学）；Departamento de Física, Universidad de Oviedo（奥维耶多大学物理系）；ASturias RAw Materials Institute (ASRAM), Universidad de Oviedo（奥维耶多大学阿斯特里亚斯原材料研究所）；Department of Condensed Matter Physics Faculty of Mathematics and Physics Charles University（查理大学数学与物理学院凝聚态物理系）
Improving Reliability of Machine Learned Interatomic Potentials With Physics-Informed Pretraining
College of Computing, Georgia Institute of Technology（佐治亚理工学院计算学院）；School of Computational Science and Engineering, Georgia Institute of Technology（佐治亚理工学院计算科学与工程学院）
