Advancements in computing power have made it possible to numerically simulate large-scale fluid-mechanical and/or particulate systems, many of which are integral to core industrial processes. The discrete element method (DEM) provides one of the most accurate representations of a wide range of physical systems involving granular materials. Additionally, DEM can be integrated with grid-based computational fluid dynamics (CFD) methods, enabling the simulation of chemical processes taking place, e.g., in fluidized beds.However, DEM is computationally intensive because of the intrinsic multiscale nature of particulate systems, restricting either the duration of simulations or the number of particles that can be simulated. Towards this end, NeuralDEM presents a first end-to-end approach to replace slow and computationally demanding DEM routines with fast deep learning surrogates.NeuralDEM treats the Lagrangian discretization of DEM as an underlying continuous field, while simultaneously modeling macroscopic behavior directly as additional auxiliary fields using ``multi-branch neural operators'', enabling fast and scalable neural surrogates.NeuralDEM will open many new doors to advanced engineering and much faster process cycles.