Latent Ewald summation for machine learning of long-range interactions
This addresses the issue of inaccurate predictions in molecular simulations 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 machine learning interatomic potentials (MLIPs) neglecting long-range interactions like electrostatic and dispersion forces, which can cause unphysical predictions in systems such as charged dimers and water interfaces. They introduced a method that learns a latent variable from local descriptors and applies Ewald summation, effectively eliminating artifacts with only about twice the computational cost of short-range MLIPs.
Machine learning interatomic potentials (MLIPs) often neglect long-range interactions, such as electrostatic and dispersion forces. In this work, we introduce a straightforward and efficient method to account for long-range interactions by learning a latent variable from local atomic descriptors and applying an Ewald summation to this variable. We demonstrate that in systems including charged and polar molecular dimers, bulk water, and water-vapor interface, standard short-ranged MLIPs can lead to unphysical predictions even when employing message passing. The long-range models effectively eliminate these artifacts, with only about twice the computational cost of short-range MLIPs.