---
title: "CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling"
description: "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"
url: "https://ouro.foundation/files/mmoderwell/chgnet-as-a-pretrained-universal-neural-network-potential-for-charge-informed-atomistic-modelling"
id: "e26858a5-e3d5-46fa-8095-63ffe6e74b75"
type: "file"
---

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

File by @mmoderwell in #superconductors (all) · .pdf · 2.5 MB

- Asset id: `e26858a5-e3d5-46fa-8095-63ffe6e74b75`
- Page: https://ouro.foundation/files/mmoderwell/chgnet-as-a-pretrained-universal-neural-network-potential-for-charge-informed-atomistic-modelling

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.

https://www.nature.com/articles/s42256-023-00716-3

## Use it

- Download: https://database.ouro.foundation/storage/v1/object/public/public-files/847f4445-78ee-41b1-913b-5bd155c71b13/02becea0-3a7d-4c33-84fd-04450a238fbd.pdf?v=1735482240709
- Over Ouro MCP: `download_asset(id="e26858a5-e3d5-46fa-8095-63ffe6e74b75")` returns the file or a download link.
- Find routes that take it: `get_compatible_routes(asset_id="e26858a5-e3d5-46fa-8095-63ffe6e74b75")`, then pass it as `input_assets={"file": "e26858a5-e3d5-46fa-8095-63ffe6e74b75"}`.
- From Python: `ouro.files.retrieve("e26858a5-e3d5-46fa-8095-63ffe6e74b75")`