# CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling

arXiv: https://arxiv.org/abs/2302.14231 · HTML: https://mlsanity.com/paper/2302.14231/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 94 references that are in the map.
- First posted on arXiv 28 Feb 2023.

## Builds on (most cited first, 10 of 10)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [Directional Message Passing for Molecular Graphs](https://mlsanity.com/paper/2003.03123/) (2020)
- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [e3nn: Euclidean Neural Networks](https://mlsanity.com/paper/2207.09453/) (2022)
- [SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects](https://mlsanity.com/paper/2105.00304/) (2021)
- [Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations](https://mlsanity.com/paper/2210.07237/) (2022)
- [Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry](https://mlsanity.com/paper/2105.14655/) (2021)
- [TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations](https://mlsanity.com/paper/1912.01398/) (2019)

## Built on by (most cited first, 13 of 13)

- [Orb: A Fast, Scalable Neural Network Potential](https://mlsanity.com/paper/2410.22570/) (2024)
- [Reinforcement Fine-Tuning for Materials Design](https://mlsanity.com/paper/2504.02367/) (2025)
- [Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm](https://mlsanity.com/paper/2309.06710/) (2023)
- [LeMat-Traj: A Scalable and Unified Dataset of Materials Trajectories for Atomistic Modeling](https://mlsanity.com/paper/2508.20875/) (2025)
- [MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models](https://mlsanity.com/paper/2512.21231/) (2025)
- [Efficient and Accurate Spatial Mixing of Machine Learned Interatomic Potentials for Materials Science](https://mlsanity.com/paper/2502.19081/) (2025)
- [Better without U: Impact of Selective Hubbard U Correction on Foundational MLIPs](https://mlsanity.com/paper/2601.21056/) (2026)
- [TriForces: Augmenting Atomistic GNNs for Transferable Representations](https://mlsanity.com/paper/2605.20581/) (2026)
- [Improving Molecular Modeling with Geometric GNNs: an Empirical Study](https://mlsanity.com/paper/2407.08313/) (2024)
- [On the practical applicability of modern DFT functionals for chemical computations. Case study of DM21 applicability for geometry optimization](https://mlsanity.com/paper/2501.12149/) (2025)
- [Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations](https://mlsanity.com/paper/2508.10841/) (2025)
- [Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data](https://mlsanity.com/paper/2604.15380/) (2026)
- [Generative Discovery of Magnetic Insulators under Competing Physical Constraints](https://mlsanity.com/paper/2604.21073/) (2026)

## Abstract (arXiv)

The simulation of large-scale systems with complex electron interactions remains one of the greatest challenges for the atomistic modeling of materials. Although classical force fields often fail to describe the coupling between electronic states and ionic rearrangements, the more accurate textitab-initio molecular dynamics suffers from computational complexity that prevents long-time and large-scale simulations, which are essential to study many technologically relevant phenomena, such as reactions, ion migrations, phase transformations, and degradation. In this work, we present the Crystal Hamiltonian Graph neural Network (CHGNet) as a novel machine-learning interatomic potential (MLIP), using a graph-neural-network-based force field to model a 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 static and relaxation trajectories of ~ 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 critically analyze the significance of including charge information for capturing appropriate chemistry, and we provide new insights into ionic systems with additional electronic degrees of freedom that can not be observed by previous MLIPs.