Development of a New Parameter Optimization Scheme for a Reactive Force Field (ReaxFF) Based on a Machine Learning Approach

Abstract

Reactive molecular dynamics (MD) simulation is performed using a reactive force field (ReaxFF). To this end, we developed a new method to optimize the ReaxFF parameters based on a machine learning approach. This approach combines the $k$-nearest neighbor and random forest regressor algorithm to efficiently locate several possible ReaxFF parameter sets, thereby the optimized ReaxFF parameter can predict physical properties even in a high-temperature condition within a small effort of parameter refinement. As a pilot test of the developed approach, the optimized ReaxFF parameter set was applied to perform chemical vapor deposition (CVD) of an $\alpha$-Al$_2$O$_3$ crystal. The crystal structure of $\alpha$-Al$_2$O$_3$ was reasonably reproduced even at a relatively high temperature (2000 K). The reactive MD simulation suggests that the (11$\overline{2}$0) surface grows faster than the (0001) surface, indicating that the developed parameter optimization technique could be used for understanding the chemical reaction in the CVD process.