Multi-reward Reinforcement Learning Based Bond-Order Potential to Study Strain-Assisted Phase Transitions in Phosphorene.
J Phys Chem Lett
; 13(7): 1886-1893, 2022 Feb 24.
Article
de En
| MEDLINE
| ID: mdl-35175062
ABSTRACT
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 (α-P) to blue phosphorene (ß-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.
Texte intégral:
1
Collection:
01-internacional
Base de données:
MEDLINE
Langue:
En
Journal:
J Phys Chem Lett
Année:
2022
Type de document:
Article
Pays d'affiliation:
États-Unis d'Amérique