Neural network force field (NNFF) is a method for performing regression on atomic structure-force relationships, bypassing expensive quantum mechanics calculation which prevents the execution of long ab-initio quality molecular dynamics simulations. However, most NNFF methods for complex multi-element atomic systems indirectly predict atomic force vectors by exploiting just atomic structure rotation-invariant features and the network-feature spatial derivatives which are computationally expensive. We develop a staggered NNFF architecture exploiting both rotation-invariant and covariant features separately to directly predict atomic force vectors without using spatial derivatives, thereby reducing expensive structural feature calculation by ~180-480x. This acceleration enables us to develop NNFF which directly predicts atomic forces in complex ternary and quaternary-element extended systems comprised of long polymer chains, amorphous oxide, and surface chemical reactions. The staggered rotation-invariant-covariant architecture described here can also directly predict complex covariant vector outputs from local physical structures in domains beyond computational material science.
@article{arxiv.1905.02791,
title = {Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex Multi-Element Extended Systems},
author = {Jonathan P. Mailoa and Mordechai Kornbluth and Simon L. Batzner and Georgy Samsonidze and Stephen T. Lam and Chris Ablitt and Nicola Molinari and Boris Kozinsky},
journal= {arXiv preprint arXiv:1905.02791},
year = {2019}
}