Benchmarking CHGNet Universal Machine Learning Interatomic Potential against DFT and EXAFS: The Case of Layered WS2 and MoS2
- 13 August 2025
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 21 (16) , 8142-8150
Abstract
Universal machine learning interatomic potentials (uMLIPs) deliver near ab initio accuracy in energy and force calculations at a low computational cost, making them invaluable for materials modeling. Although uMLIPs are pretrained on vast ab initio data sets, rigorous validation remains essential for their ongoing adoption. In this study, we use the CHGNet uMLIP to model thermal disorder in isostructural layered 2Hc-WS2 and 2Hc-MoS2, benchmarking it against ab initio data and extended X-ray absorption fine structure (EXAFS) spectra, which capture thermal variations in bond lengths and angles. Fine-tuning CHGNet with compound-specific ab initio (density functional theory (DFT)) data mitigates the systematic softening (i.e., force underestimation) typical of uMLIPs and simultaneously improves the alignment between molecular dynamics-derived and experimental EXAFS spectra. While fine-tuning with a single DFT structure is viable, using ∼100 structures is recommended to accurately reproduce EXAFS spectra and achieve DFT-level accuracy. Benchmarking the CHGNet uMLIP against both DFT and experimental EXAFS data reinforces confidence in its performance and provides guidance for determining optimal fine-tuning data set sizes.Keywords
All Related Versions
Funding Information
- European Regional Development Fund (1.1.1.9/LZP/1/24/016)
- Latvijas Zinātnes Padome (LZP-2023/1-0528)
This publication has 76 references indexed in Scilit:
- Systematic assessment of various universal machine‐learning interatomic potentialsMaterials Genome Engineering Advances, 2024
- Density functional and force field modeling of multi-walled WS2 nanotubesComputational and Theoretical Chemistry, 2023
- Validation of moment tensor potentials for fcc and bcc metals using EXAFS spectraComputational Materials Science, 2022
- DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamicsComputer Physics Communications, 2018
- Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentialsJournal of Computational Physics, 2015
- Effect of the damping function in dispersion corrected density functional theoryJournal of Computational Chemistry, 2011
- Ab initio theory and calculations of X-ray spectraComptes Rendus. Physique, 2008
- A practical introduction to multiple scattering theoryJournal of Alloys and Compounds, 2005
- Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis setComputational Materials Science, 1996
- Crystal structures of tungsten disulfide and diselenideJournal of Solid State Chemistry, 1987