Automated discovery of a robust interatomic potential for aluminum.

Smith, Justin S; Nebgen, Benjamin; Mathew, Nithin; Chen, Jie; Lubbers, Nicholas; Burakovsky, Leonid; Tretiak, Sergei; Nam, Hai Ah et al. · Nat Commun · 2021

basic_science · Level V

Where this comes from

Abstract

Machine learning, trained on quantum mechanics (QM) calculations, is a powerful tool for modeling potential energy surfaces. A critical factor is the quality and diversity of the training dataset. Here we present a highly automated approach to dataset construction and demonstrate the method by building a potential for elemental aluminum (ANI-Al). In our active learning scheme, the ML potential under development is used to drive non-equilibrium molecular dynamics simulations with time-varying applied temperatures. Whenever a configuration is reached for which the ML uncertainty is large, new QM data is collected. The ML model is periodically retrained on all available QM data. The final ANI-Al potential makes very accurate predictions of radial distribution function in melt, liquid-solid coexistence curve, and crystal properties such as defect energies and barriers. We perform a 1.3M atom shock simulation and show that ANI-Al force predictions shine in their agreement with new reference DFT calculations.