Machine-learning accelerated geometry optimization in molecular simulation

TL;DR

This paper introduces a neural network ensemble active learning approach to speed up geometry optimization in molecular simulations, reducing computational costs in quantum chemistry calculations.

Contribution

It presents a novel neural network ensemble method with active learning to accelerate geometry optimization across multiple configurations simultaneously.

Findings

Fewer DFT calculations needed with the new method.

Effective acceleration demonstrated on various surface and reaction cases.

Provides an accessible Python package for implementation.

Abstract

Geometry optimization is an important part of both computational materials and surface science because it is the path to finding ground state atomic structures and reaction pathways. These properties are used in the estimation of thermodynamic and kinetic properties of molecular and crystal structures. This process is slow at the quantum level of theory because it involves an iterative calculation of forces using quantum chemical codes such as density functional theory (DFT), which are computationally expensive, and which limit the speed of the optimization algorithms. It would be highly advantageous to accelerate this process because then one could either do the same amount of work in less time, or more work in the same time. In this work, we provide a neural network (NN) ensemble based active learning method to accelerate the local geometry optimization for multiple configurations simultaneously. We illustrate the acceleration on several case studies including bare metal surfaces, surfaces with adsorbates, and nudged elastic band (NEB) for two reactions. In all cases the accelerated method requires fewer DFT calculations than the standard method. In addition, we provide an ASE-optimizer Python package to make the usage of the NN ensemble active learning for geometry optimization easier.