Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911147446239232 |
|---|---|
| author | Žguns, Pjotrs Pudza, Inga Kuzmin, Alexei |
| author_facet | Žguns, Pjotrs Pudza, Inga Kuzmin, Alexei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08498 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2 Žguns, Pjotrs Pudza, Inga Kuzmin, Alexei Materials Science 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. |
| title | Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2 |
| topic | Materials Science |
| url | https://arxiv.org/abs/2509.08498 |