Using dimensionality reduction and clustering techniques to classify space plasma regimes

TL;DR

This paper introduces a novel classification method for space plasma regimes using dimensionality reduction and clustering on electron distribution functions, revealing more complex plasma structures than traditional models.

Contribution

It applies multiple machine learning algorithms to classify plasma regions based on distribution functions, uncovering eight distinct plasma groups in Earth's magnetotail.

Findings

Identified eight distinct plasma distribution groups.

Revealed more complex plasma structures than traditional three-region models.

Achieved clear distinctions between classified regions and existing classifications.

Abstract

Collisionless space plasma environments are typically characterised by distinct particle populations. Although moments of their velocity distribution functions help in distinguishing different plasma regimes, the distribution functions themselves provide more comprehensive information about the plasma state, especially at times when the distribution function includes non-thermal effects. Unlike moments, however, distribution functions are not easily characterised by a small number of parameters, making their classification more difficult to achieve. In order to perform this classification, we propose to distinguish between the different plasma regions by applying dimensionality reduction and clustering methods to electron distributions in pitch angle and energy space. We utilise four separate algorithms to achieve our plasma classifications: autoencoders, principal component analysis, mean shift, and agglomerative clustering. We test our classification algorithms by applying our scheme to data from the Cluster-PEACE instrument measured in the Earth's magnetotail. Traditionally, it is thought that the Earth's magnetotail is split into three different regions (the plasma sheet, the plasma sheet boundary layer, and the lobes), that are primarily defined by their plasma characteristics. Starting with the ECLAT database with associated classifications based on the plasma parameters, we identify 8 distinct groups of distributions, that are dependent upon significantly more complex plasma and field dynamics. By comparing the average distributions as well as the plasma and magnetic field parameters for each region, we relate several of the groups to different plasma sheet populations, and the rest we attribute to the plasma sheet boundary layer and the lobes. We find clear distinctions between each of our classified regions and the ECLAT results.