Benchmarking CHGNet Universal Machine Learning Interatomic Potential against DFT and EXAFS: The Case of Layered WS₂...

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 2H_c-WS₂ and 2H_c-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.