期刊
JOURNAL OF PHYSICAL CHEMISTRY LETTERS
卷 13, 期 7, 页码 1886-1893出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jpclett.1c03551
关键词
-
类别
资金
- U.S. Department of Energy through BES Award [DE-SC0021201]
- U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences [DE-AC02-06CH11357, DE-AC05-00OR22725]
- Office of Science of the US Department of Energy [DE-AC02-05CH11231]
- U.S. Department of Energy (DOE) [DE-SC0021201] Funding Source: U.S. Department of Energy (DOE)
In this study, a multi-reward reinforcement learning approach is introduced for training a flexible bond-order potential for 2D phosphorene. The approach combines a continuous action space Monte Carlo tree search algorithm with an efficient multiobjective optimization scheme, successfully capturing various properties of 2D phosphorene polymorphs. Molecular dynamics simulations reveal the impact of temperature and strain rate on a phase transition, with a decrease in critical strain observed with increasing temperature. The underlying atomistic mechanisms are discussed.
We introduce a multi-reward reinforcement learning (RL) approach to train a flexible bond-order potential (BOP) for 2D phosphorene based on ab initio training data sets. Our approach is based on a continuous action space Monte Carlo tree search algorithm that is general and scalable and presents an efficient multiobjective optimization scheme for high-dimensional materials design problems. As a proof-of-concept, we deploy this scheme to parametrize multiple structural and dynamical properties of 2D phosphorene polymorphs. Our RL-trained BOP model adequately captures the structure, energetics, transformation barriers, equation of state, elastic constants, and phonon dispersions of various 2D P polymorphs. We use this model to probe the impact of temperature and strain rate on the phase transition from black (alpha-P) to blue phosphorene (beta-P) through molecular dynamics simulations. A decrease in critical strain for this phase transition with increase in temperature is observed, and the underlying atomistic mechanisms are discussed.
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