Physics-informed Neural-Network Software for Molecular Dynamics Applications
This provides a specialized tool for researchers in computational chemistry and materials science to streamline physics-informed neural network applications in molecular dynamics, though it appears incremental as an implementation-focused software.
The researchers developed PND, a physics-informed neural network software for molecular dynamics simulations that allows flexible implementation of equations, conditions, and conservation laws as loss functions, and includes a parallel MD engine to accelerate PINN-based development.
We have developed a novel differential equation solver software called PND based on the physics-informed neural network for molecular dynamics simulators. Based on automatic differentiation technique provided by Pytorch, our software allows users to flexibly implement equation of atom motions, initial and boundary conditions, and conservation laws as loss function to train the network. PND comes with a parallel molecular dynamics (MD) engine in order for users to examine and optimize loss function design, and different conservation laws and boundary conditions, and hyperparameters, thereby accelerate the PINN-based development for molecular applications.