A Novel Method to Train Classification Models for Structure Detection in In-situ Spacecraft Data

Abstract

We present a method for creating spacecraft-like data which can be used to train Machine Learning (ML) models to detect and classify structures in in-situ spacecraft data. First, we use the Grad-Shafranov (GS) equation to numerically solve for several magnetohydrostatic equilibria which are variations on a known analytic equilibrium. These equilibria are then used as the initial conditions for Particle-In-Cell (PIC) simulations in which the structures of interest are observed and labeled. We then take one-dimensional slices through the simulations to replicate what a spacecraft collecting data from the simulation would observe. This sliced data then can be used as training data for the initial training of ML models intended for use on spacecraft data. We demonstrate the method applied to the problem of detecting small-scale plasmoids in the magnetotail, which is important for understanding complex magnetotail reconnection dynamics. The simple 1D classifier we train is able to detect 77% of the plasmoid points in the dataset but also produces a large number of false positives. Our further work on this example problem is detailed, and further potential uses of the method are discussed.

Laboratory Study of Collisionless Magnetic Reconnection

“…Furthermore, to process a huge amount of existing and new observational, numerical, and laboratory data for statistical studies, there exist promising opportunities to use novel techniques based on data science such as machine learning (e.g. Bergstedt and Ji 2023).…”