CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling

Bowen Deng, Peichen Zhong, Kyu Jung Jun, Janosh Riebesell, Kevin Han, Christopher J. Bartel, Gerbrand Ceder

Research output: Contribution to journalArticlepeer-review

130 Scopus citations

Abstract

Large-scale simulations with complex electron interactions remain one of the greatest challenges for atomistic modelling. Although classical force fields often fail to describe the coupling between electronic states and ionic rearrangements, the more accurate ab initio molecular dynamics suffers from computational complexity that prevents long-time and large-scale simulations, which are essential to study technologically relevant phenomena. Here we present the Crystal Hamiltonian Graph Neural Network (CHGNet), a graph neural network-based machine-learning interatomic potential (MLIP) that models the universal potential energy surface. CHGNet is pretrained on the energies, forces, stresses and magnetic moments from the Materials Project Trajectory Dataset, which consists of over 10 years of density functional theory calculations of more than 1.5 million inorganic structures. The explicit inclusion of magnetic moments enables CHGNet to learn and accurately represent the orbital occupancy of electrons, enhancing its capability to describe both atomic and electronic degrees of freedom. We demonstrate several applications of CHGNet in solid-state materials, including charge-informed molecular dynamics in LixMnO2, the finite temperature phase diagram for LixFePO4 and Li diffusion in garnet conductors. We highlight the significance of charge information for capturing appropriate chemistry and provide insights into ionic systems with additional electronic degrees of freedom that cannot be observed by previous MLIPs.

Original languageEnglish (US)
Pages (from-to)1031-1041
Number of pages11
JournalNature Machine Intelligence
Volume5
Issue number9
DOIs
StatePublished - Sep 2023

Bibliographical note

Publisher Copyright:
© 2023, This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.

Fingerprint

Dive into the research topics of 'CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling'. Together they form a unique fingerprint.

Cite this