Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations

2026-01-18

AI Summary

This work proposes the first application of graph neural networks (Graph-FM/EFM) to global hybrid Vlasov simulations of solar wind–magnetosphere interactions, addressing the prohibitive computational cost of full five-dimensional modeling that hinders real-time forecasting. The authors develop both deterministic and probabilistic surrogate models that enforce physical consistency and provide calibrated uncertainty quantification. Divergence-free magnetic fields are ensured through a dedicated divergence penalty term, while ensemble forecast calibration is optimized using the continuous ranked probability score (CRPS). Evaluated on a 2D spatial grid comprising 670,000 cells, the model achieves over two orders of magnitude speedup on a single GPU compared to the original Vlasiator simulation running on 100 CPUs, accurately reproducing magnetospheric responses across varying initial plasma densities and delivering reliable uncertainty estimates.

Technology Category

• Reasoning under Uncertainty: Graphical Models
• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Hybrid-Vlasov simulations resolve ion-kinetic effects for modeling the solar wind-magnetosphere interaction, but even 5D (2D + 3V) simulations 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. The initial ion number density is systematically varied, while the grid spacing is held constant, to scan the ratio of the characteristic ion skin depth to the numerical grid size. Using a graph neural network architecture operating on the 2D spatial simulation grid comprising 670k cells, we demonstrate that both a deterministic forecasting model (Graph-FM) and a probabilistic ensemble forecasting model (Graph-EFM) based on a latent variable formulation are capable of producing accurate predictions of future plasma states. A divergence penalty is incorporated during training to encourage divergence-freeness in the magnetic fields and improve physical consistency. For the probabilistic model, a continuous ranked probability score objective is added to improve the calibration of the ensemble forecasts. When trained, the emulators achieve more than two orders of magnitude speedup in generating the next time step relative to the original simulation on a single GPU compared to 100 CPUs for the Vlasiator runs, while closely matching physical magnetospheric response of the different runs. These results demonstrate that machine learning offers a way to make hybrid-Vlasov simulation tractable for real-time use while providing forecast uncertainty.

Problem

• hybrid-Vlasov simulation
• solar wind-magnetosphere interaction
• computational cost
• ion-kinetic effects
• real-time forecasting

Innovation

• graph neural networks
• hybrid-Vlasov simulation
• probabilistic forecasting
• divergence-free constraint
• surrogate modeling