FlashMD: long-stride, universal prediction of molecular dynamics
This work addresses the time-scale limitation in molecular dynamics for researchers in computational chemistry and materials science, representing a novel method for a known bottleneck rather than an incremental improvement.
The authors tackled the problem of molecular dynamics simulations being constrained to minuscule time steps due to fast atomic motion, and developed FlashMD to predict atomic evolution over strides one to two orders of magnitude longer, enabling simulations to reach longer time scales needed for modeling microscopic processes.
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 such a long-stride 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.