Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909818949730304 |
|---|---|
| author | Le, Hung Abbas, Sherif Nguyen, Minh Hoang Do, Van Dai Nguyen, Huu Hiep Nguyen, Dung |
| author_facet | Le, Hung Abbas, Sherif Nguyen, Minh Hoang Do, Van Dai Nguyen, Huu Hiep Nguyen, Dung |
| contents | Efficient molecular dynamics (MD) simulation is vital for understanding atomic-scale processes in materials science and biophysics. Traditional density functional theory (DFT) methods are computationally expensive, which limits the feasibility of long-term simulations. We propose a novel approach that formulates MD simulation as a time-series forecasting problem, enabling advanced forecasting models to predict atomic trajectories via displacements rather than absolute positions. We incorporate a physics-informed loss and inference mechanism based on DFT-parametrised pair-wise Morse potential functions that penalize unphysical atomic proximity to enforce physical plausibility. Our method consistently surpasses standard baselines in simulation accuracy across diverse materials. The results highlight the importance of incorporating physics knowledge to enhance the reliability and precision of atomic trajectory forecasting. Remarkably, it enables stable modeling of thousands of MD steps in minutes, offering a scalable alternative to costly DFT simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01206 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting Le, Hung Abbas, Sherif Nguyen, Minh Hoang Do, Van Dai Nguyen, Huu Hiep Nguyen, Dung Machine Learning Efficient molecular dynamics (MD) simulation is vital for understanding atomic-scale processes in materials science and biophysics. Traditional density functional theory (DFT) methods are computationally expensive, which limits the feasibility of long-term simulations. We propose a novel approach that formulates MD simulation as a time-series forecasting problem, enabling advanced forecasting models to predict atomic trajectories via displacements rather than absolute positions. We incorporate a physics-informed loss and inference mechanism based on DFT-parametrised pair-wise Morse potential functions that penalize unphysical atomic proximity to enforce physical plausibility. Our method consistently surpasses standard baselines in simulation accuracy across diverse materials. The results highlight the importance of incorporating physics knowledge to enhance the reliability and precision of atomic trajectory forecasting. Remarkably, it enables stable modeling of thousands of MD steps in minutes, offering a scalable alternative to costly DFT simulations. |
| title | Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.01206 |