Force and stress calculation with neural network wavefunction for solids

Abstract

Accurate ab initio calculations of real solids are of fundamental importance in fields such as chemistry, phases and materials science. Recently, variational Monte Carlo (VMC) based on neural network wavefunction has been developed as a promising option to solve the existing challenges in ab initio calculations. In this study, we discuss the calculation of interatomic force and stress tensor of real solids with neural network--based VMC method. A new scheme of computing force is proposed based on the space warp coordination transformation method, which achieves better accuracy, efficiency and robustness than existing methods. In addition, we also designed new periodic features of neural network to further improve the robustness of force calculations for different lattices. This work paves the way for further extending the application of machine learning quantum Monte Carlo in materials modelling.