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 α-Al2O3 crystal. The crystal structure of α-Al2O3 was reasonably reproduced even at a relatively high temperature (2000 K). The reactive MD simulation suggests that the (1120) 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.
@article{arxiv.1812.03256,
title = {Development of a New Parameter Optimization Scheme for a Reactive Force Field (ReaxFF) Based on a Machine Learning Approach},
author = {Hiroya Nakata and Shandan Bai},
journal= {arXiv preprint arXiv:1812.03256},
year = {2018}
}