期刊
NATURE COMMUNICATIONS
卷 13, 期 1, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s41467-022-32294-0
关键词
-
资金
- Bosch Research LLC
- National Science Foundation [1808162, 2003725]
- US Department of Energy (DOE), Office of Science, Office of Basic Energy Sciences (BES) [DE-SC0012573]
- National Science Foundation Graduate Research Fellowship Program [DGE1745303]
- Cannon cluster, FAS Division of Science, Research Computing Group at Harvard University
- DOE Office of Science User Facility [DE-AC02-05CH11231]
- Division Of Materials Research
- Direct For Mathematical & Physical Scien [1808162] Funding Source: National Science Foundation
- Office of Advanced Cyberinfrastructure (OAC)
- Direct For Computer & Info Scie & Enginr [2003725] Funding Source: National Science Foundation
This article describes a Bayesian active learning framework for atomistic modeling of chemically reactive systems. The method enables autonomous on-the-fly training of fast and accurate reactive many-body force fields during molecular dynamics simulations, and automatically determines whether additional training data are needed.
Atomistic modeling of chemically reactive systems has so far relied on either expensive ab initio methods or bond-order force fields requiring arduous parametrization. Here, we describe a Bayesian active learning framework for autonomous on-the-fly training of fast and accurate reactive many-body force fields during molecular dynamics simulations. At each time-step, predictive uncertainties of a sparse Gaussian process are evaluated to automatically determine whether additional ab initio training data are needed. We introduce a general method for mapping trained kernel models onto equivalent polynomial models whose prediction cost is much lower and independent of the training set size. As a demonstration, we perform direct two-phase simulations of heterogeneous H-2 turnover on the Pt(111) catalyst surface at chemical accuracy. The model trains itself in three days and performs at twice the speed of a ReaxFF model, while maintaining much higher fidelity to DFT and excellent agreement with experiment. Uncertainty-aware machine learning models are used to automate the training of reactive force fields. The method is used here to simulate hydrogen turnover on a platinum surface with unprecedented accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据