Machine Learning of Reactive Potentials

被引：30

作者：

Yang, Yinuo ^{[1
]}

Zhang, Shuhao ^{[2
]}

Ranasinghe, Kavindri D. ^{[1
]}

Isayev, Olexandr ^{[2
]}

Roitberg, Adrian E. ^{[1
]}

机构：

[1] Univ Florida, Dept Chem, Gainesville, FL 32611 USA

[2] Carnegie Mellon Univ, Dept Chem, Pittsburgh, PA USA

来源：

ANNUAL REVIEW OF PHYSICAL CHEMISTRY | 2024年 / 75卷

基金：

美国国家科学基金会;

关键词：

machine learning; neural networks; chemical reactions; potential energy surface; computational chemistry; MOLECULAR-DYNAMICS; FORCE-FIELD; ENERGY SURFACE; SIMULATIONS; CHEMISTRY; APPROXIMATION; ACCURACY; DATABASE;

D O I：

10.1146/annurev-physchem-062123-024417

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

In the past two decades, machine learning potentials (MLPs) have driven significant developments in chemical, biological, and material sciences. The construction and training of MLPs enable fast and accurate simulations and analysis of thermodynamic and kinetic properties. This review focuses on the application of MLPs to reaction systems with consideration of bond breaking and formation. We review the development of MLP models, primarily with neural network and kernel-based algorithms, and recent applications of reactive MLPs (RMLPs) to systems at different scales. We show how RMLPs are constructed, how they speed up the calculation of reactive dynamics, and how they facilitate the study of reaction trajectories, reaction rates, free energy calculations, and many other calculations. Different data sampling strategies applied in building RMLPs are also discussed with a focus on how to collect structures for rare events and how to further improve their performance with active learning.

引用

页码：371 / 395

页数：25

共 141 条

[1] Active learning accelerates ab initio molecular dynamics on reactive energy surfaces [J].