Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
arXiv:2509.08498 · doi:10.1021/acs.jctc.5c00955
Abstract
Universal machine learning interatomic potentials (uMLIPs) deliver near ab initio accuracy in energy and force calculations at low computational cost, making them invaluable for materials modeling. Although uMLIPs are pre-trained on vast ab initio datasets, 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 (DFT) data mitigates the systematic softening (i.e., force underestimation) typical of uMLIPs and simultaneously improves 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 dataset sizes.
References in corpus (21)
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
- ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
- Moment Tensor Potentials: a class of systematically improvable interatomic potentials
- A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
- A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
- Atomistic Line Graph Neural Network for Improved Materials Property Predictions
- On-the-fly machine learning force field generation: Application to melting points
- Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
- Machine learning a general purpose interatomic potential for silicon
- Lattice dynamics and correlated atomic motion from the atomic pair distribution function
- How to validate machine-learned interatomic potentials
- Phase transitions in inorganic halide perovskites from machine learning potentials
- Interlayer Coupling in Two-Dimensional Semiconductor Materials
- Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
- Why is EXAFS analysis for multicomponent metals so hard? Challenges and opportunities for measuring ordering in complex concentrated alloys using x-ray absorption spectroscopy
- Treatment of disorder effects in X-ray absorption spectra beyond the conventional approach
- Effect of cation-disorder on lithium transport in halide superionic conductors
- Advanced approach to the local structure reconstruction and theory validation on the example of the W L-edge extended X-ray absorption fine structure of tungsten
- Unraveling the interlayer and intralayer coupling in two-dimensional layered MoS by X-ray absorption spectroscopy and ab initio molecular dynamics simulations
- k-Means Clustering in Fingerprint-Based Configuration Selection for Fitting Interatomic Potentials