Date of Award

Fall 2024

Project Type

Dissertation

Program or Major

Physics

Degree Name

Doctor of Philosophy

First Advisor

Joachim Raeder

Second Advisor

Matthew Argall

Third Advisor

Banafsheh Ferdousi

Abstract

The use of supervised methods in space science have demonstrated powerful capability in classification tasks, but purely unsupervised methods have been less utilized for the classification of spacecraft observations. We use a combination of unsupervised methods, being principal component analysis, self-organizing maps, and hierarchical agglomerative clustering, to classify THEMIS and MMS observations as having occurred in the magnetosphere, magnetosheath, or the solar wind. The resulting classification are validated visually by analyzing the distribution of classifications and studying individual time series as well as by comparison to the labeled dataset of a previous model, against which ours has an accuracy of 99.4$\%$. The model has a variety of applications beyond region classification such as deeper hierarchical analysis, magnetopause and bow shock crossing identification, and identification of bursty bulk flows, hot flow anomalies, and foreshock bubbles. Then using the bow shock crossings inferred from the previous model as well as the results of another machine learning model and an online bow shock crossing catalogue, we create a bow shock dataset of almost 16k crossings. An ensemble of neural networks are trained to predict the coefficients of a bow shock model function using traditional bow shock parameters as well as magnetic clock and cone angles. The small size of the dataset means that typical partitioning of the training set cannot reasonably be done, so the ensemble members are bootstrap-trained. We show the ensemble to perform better than a single model trained on the full dataset. The model results show mixed agreement with previous observations and performs better than the Chao model for varying clock and cone angles and for nightside bow shock crossings, but slightly underperforms for dayside crossings.

Share

COinS