Graph Representation of the Magnetic Field Topology in High-Fidelity Plasma Simulations for Machine Learning Applications
This work addresses the largely open scientific problem of analyzing magnetic field topology in plasma physics, with potential impact for machine learning applications in high-fidelity simulations.
The authors tackled the problem of detecting and characterizing magnetic reconnection in 3D plasma simulations by proposing a scalable pipeline for topological data analysis and spatiotemporal graph representation of magnetic fields, demonstrating it on Earth's magnetosphere simulations from the Vlasiator supercomputer.
Topological analysis of the magnetic field in simulated plasmas allows the study of various physical phenomena in a wide range of settings. One such application is magnetic reconnection, a phenomenon related to the dynamics of the magnetic field topology, which is difficult to detect and characterize in three dimensions. We propose a scalable pipeline for topological data analysis and spatiotemporal graph representation of three-dimensional magnetic vector fields. We demonstrate our methods on simulations of the Earth's magnetosphere produced by Vlasiator, a supercomputer-scale Vlasov theory-based simulation for near-Earth space. The purpose of this work is to challenge the machine learning community to explore graph-based machine learning approaches to address a largely open scientific problem with wide-ranging potential impact.