Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations

ArXi:2601.12614v3 Announce Type: replace-cross Hybrid-Vlaso simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are computationally expensive. We show that graph-based machine learning emulators can learn the spatiotemporal evolution of electromagnetic fields and lower order moments of ion velocity distribution in the near-Earth space environment from four 5D Vlasiator runs performed with identical steady solar wind conditions.