Open access
Jul 2026
Molecular physics-informed neural network (mPINN) for solving the molecular dynamics equation of motion with energy conservation
The results demonstrate that the mPINN architecture functions as a reliable, physics-constrained ML framework capable of delivering high-fidelity trajectory predictions for complex multi-body molecular systems.
T. Muther, V. Pham, A. K. Dahaghi
· Machine Learning: Science an... · 0 citations