Using graph neural network and symbolic regression to model disordered systems

Abstract

Abstract The key to modeling disordered systems lies in accurately simulating atomic trajectories, typically achieved through molecular dynamic (MD) simulation. The accuracy of MD simulations depends on the precision of the interatomic potential function, which dictates the calculations of atom movements. Traditionally, deriving interatomic potential function relies on extensive prior physical knowledge and high computational cost. This study introduces a novel approach that integrates machine learning with molecular dynamic methods to provide precise interatomic potential energy calculations for disordered systems.