Exciting DeePMD: Learning excited state energies, forces, and non-adiabatic couplings
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913547975393280 |
|---|---|
| author | Dupuy, Lucien Maitra, Neepa T. |
| author_facet | Dupuy, Lucien Maitra, Neepa T. |
| contents | We extend the DeePMD neural network architecture to predict electronic structure properties necessary to perform non-adiabatic dynamics simulations. While learning the excited state energies and forces follows a straightforward extension of the DeePMD approach for ground-state energies and forces, how to learn the map between the non-adiabatic coupling vectors (NACV) and the local chemical environment descriptors of DeePMD is less trivial. Most implementations of machine-learning-based non-adiabatic dynamics inherently approximate the NACVs, with an underlying assumption that the energy-difference-scaled NACVs are conservative fields. We overcome this approximation, implementing the method recently introduced by Richardson [J. Chem. Phys. 158 011102 (2023)], which learns the symmetric dyad of the energy-difference-scaled NACV. The efficiency and accuracy of our neural network architecture is demonstrated through the example of the methaniminium cation CH$_2$NH$_2^+$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10881 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exciting DeePMD: Learning excited state energies, forces, and non-adiabatic couplings Dupuy, Lucien Maitra, Neepa T. Chemical Physics We extend the DeePMD neural network architecture to predict electronic structure properties necessary to perform non-adiabatic dynamics simulations. While learning the excited state energies and forces follows a straightforward extension of the DeePMD approach for ground-state energies and forces, how to learn the map between the non-adiabatic coupling vectors (NACV) and the local chemical environment descriptors of DeePMD is less trivial. Most implementations of machine-learning-based non-adiabatic dynamics inherently approximate the NACVs, with an underlying assumption that the energy-difference-scaled NACVs are conservative fields. We overcome this approximation, implementing the method recently introduced by Richardson [J. Chem. Phys. 158 011102 (2023)], which learns the symmetric dyad of the energy-difference-scaled NACV. The efficiency and accuracy of our neural network architecture is demonstrated through the example of the methaniminium cation CH$_2$NH$_2^+$. |
| title | Exciting DeePMD: Learning excited state energies, forces, and non-adiabatic couplings |
| topic | Chemical Physics |
| url | https://arxiv.org/abs/2407.10881 |