Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations
Abstract Hybrid-Vlasov 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...
Daniel Holmberg, Ivan Zaitsev, Markku Alho et al.
· Machine Learning Science and... · 0 citations