FlashMD: long-stride, universal prediction of molecular dynamics

Filippo Bigi, Sanggyu Chong, Agustinus Kristiadi, Michele Ceriotti

Keywords: molecular dynamics, atomistic modeling, geometric machine learning, statistical mechanics

TL;DR: A method for the prediction of molecular dynamics trajectories using long time steps

Abstract: Molecular dynamics (MD) provides insights into atomic-scale processes by integrating over time the equations that describe the motion of atoms under the action of interatomic forces. Machine learning models have substantially accelerated MD by providing inexpensive predictions of the forces, but they remain constrained to minuscule time integration steps, which are required by the fast time scale of atomic motion. In this work, we propose FlashMD, a method to predict the evolution of positions and momenta over strides that are between one and two orders of magnitude longer than typical MD time steps. We incorporate considerations on the mathematical and physical properties of Hamiltonian dynamics in the architecture, generalize the approach to allow the simulation of any thermodynamic ensemble, and carefully assess the possible failure modes of a direct MD approach. We validate FlashMD’s accuracy in reproducing equilibrium and time‐dependent properties, using both system‐specific and general-purpose models, extending the ability of MD simulation to reach the long time scales needed to model microscopic processes of high scientific and technological relevance.

Primary Area: Machine learning for sciences (e.g. climate, health, life sciences, physics, social sciences)

Submission Number: 22594