Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting
This provides a scalable alternative to costly DFT simulations for materials science and biophysics, though it is incremental as it builds on existing forecasting methods with physics integration.
The paper tackles the computational expense of traditional density functional theory (DFT) methods in molecular dynamics (MD) simulation by formulating MD as a time-series forecasting problem with physics-informed constraints, enabling stable modeling of thousands of MD steps in minutes and surpassing standard baselines in accuracy.
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.