Short-range $Δ$-Machine Learning: A cost-efficient strategy to transfer chemical accuracy to condensed phase systems
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_ | 1866916627507838976 |
|---|---|
| author | Mészáros, Bence Balázs Szabó, András Daru, János |
| author_facet | Mészáros, Bence Balázs Szabó, András Daru, János |
| contents | DFT-based machine-learning potentials (MLPs) are now routinely trained for condensed-phase systems, but surpassing DFT accuracy remains challenging due to the cost or unavailability of periodic reference calculations. Our previous work (PRL 2022, 129, 226001) demonstrated that high-accuracy periodic MLPs can be trained within the CCMD framework using extended yet finite reference calculations. Here, we introduce short-range $Δ$-Machine Learning (sr$Δ$ML), which builds on periodic MLPs while accurately reproducing the observables of the high-level method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16930 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Short-range $Δ$-Machine Learning: A cost-efficient strategy to transfer chemical accuracy to condensed phase systems Mészáros, Bence Balázs Szabó, András Daru, János Chemical Physics DFT-based machine-learning potentials (MLPs) are now routinely trained for condensed-phase systems, but surpassing DFT accuracy remains challenging due to the cost or unavailability of periodic reference calculations. Our previous work (PRL 2022, 129, 226001) demonstrated that high-accuracy periodic MLPs can be trained within the CCMD framework using extended yet finite reference calculations. Here, we introduce short-range $Δ$-Machine Learning (sr$Δ$ML), which builds on periodic MLPs while accurately reproducing the observables of the high-level method. |
| title | Short-range $Δ$-Machine Learning: A cost-efficient strategy to transfer chemical accuracy to condensed phase systems |
| topic | Chemical Physics |
| url | https://arxiv.org/abs/2502.16930 |