Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks

TL;DR

This paper demonstrates that bi-directional neural networks, especially Bi-LSTMs, can effectively enhance the resolution of molecular dynamics trajectories post-simulation, achieving high accuracy and robustness.

Contribution

It introduces the use of bi-directional neural networks for on-demand trajectory super-resolution in molecular dynamics, outperforming uni-directional models.

Findings

Bi-LSTMs outperform other neural network models in trajectory interpolation.

Models achieve up to 10^{-4} angstrom accuracy in reconstructing molecular vibrations.

Bi-LSTMs show robustness to noisy and complex molecular dynamics.

Abstract

Molecular dynamics simulations are a cornerstone in science, allowing to investigate from the system's thermodynamics to analyse intricate molecular interactions. In general, to create extended molecular trajectories can be a computationally expensive process, for example, when running $ab-initio$ simulations. Hence, repeating such calculations to either obtain more accurate thermodynamics or to get a higher resolution in the dynamics generated by a fine-grained quantum interaction can be time- and computationally-consuming. In this work, we explore different machine learning (ML) methodologies to increase the resolution of molecular dynamics trajectories on-demand within a post-processing step. As a proof of concept, we analyse the performance of bi-directional neural networks such as neural ODEs, Hamiltonian networks, recurrent neural networks and LSTMs, as well as the uni-directional variants as a reference, for molecular dynamics simulations (here: the MD17 dataset). We have found that Bi-LSTMs are the best performing models; by utilizing the local time-symmetry of thermostated trajectories they can even learn long-range correlations and display high robustness to noisy dynamics across molecular complexity. Our models can reach accuracies of up to 10$^{-4}$ angstroms in trajectory interpolation, while faithfully reconstructing several full cycles of unseen intricate high-frequency molecular vibrations, rendering the comparison between the learned and reference trajectories indistinguishable. The results reported in this work can serve (1) as a baseline for larger systems, as well as (2) for the construction of better MD integrators.