A Universal Graph Deep Learning Interatomic Potential for the Periodic Table

Abstract Interatomic potentials (IAPs), which describe the potential energy surface of a collection of atoms, are a fundamental input for atomistic simulations. However, existing IAPs are either fitted to narrow chemistries or too inaccurate for general applications. Here, we report a universal IAP for materials based on graph neural networks with three-body interactions (M3GNet). The M3GNet IAP was trained on the massive database of structural relaxations performed by the Materials Project over the past 10 years and has broad applications in structural relaxation, dynamic simulations and property prediction of materials across diverse chemical spaces. About 1.8 million potentially stable materials were identified from a screening of 31 million hypothetical crystal structures, demonstrating a machine learning-accelerated pathway to the discovery of synthesizable materials with exceptional properties.