Graph Representation of the Magnetic Field Topology in High-Fidelity Plasma Simulations for Machine Learning Applications

TL;DR

This paper introduces a scalable pipeline for topological analysis and graph representation of 3D magnetic fields in plasma simulations, aiming to facilitate machine learning applications in understanding magnetic phenomena.

Contribution

It presents a novel method for topological data analysis and graph modeling of magnetic fields in high-fidelity plasma simulations, specifically applied to Earth's magnetosphere.

Findings

Demonstrated on Vlasiator simulation data

Enables graph-based machine learning for magnetic reconnection detection

Provides a scalable approach for topological analysis in plasma physics

Abstract

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.