Decision tree application to satellite measurement and analysis of exospheric neutral densities

There are generally two types of models to simulate space science parameters: physics-based models and statistics-based models. The first type of model makes predictions based on physical assumptions and mathematical expressions. The second type does so based on past data, applying linear regression algorithms along with polynomial and wavelet functions. The project investigates the mechanism of small-scale changes in near- Earth space, and the interaction between the charged particles of the solar wind and Earth’s magnetosphere. We have developed a decision tree-based machine learning model that has the capability to make predictions about various physical parameters of the Earth’s magnetosphere. The training data set is provided by the Cluster II mission from ESA, courtesy of Dr. Elena Kornberg. The Cluster II is a space mission of the European Space Agency (ESA) with NASA collaboration, comprising four satellites flying in a tetrahedral formation while collecting the most detailed data yet on small- scale changes in near-Earth space, and on the interaction between the charged particles of the solar wind and Earth’s magnetosphere for a continuous period of two solar cycles (22 years). We also investigate the role of neutral dynamics in the evolution of ring current and the terrestrial magnetosphere as a whole. We study the role of the geocoronal density distribution in the ring current loss by incorporating different geocoronal models with the Hot Electron and Ion Drift Integrator (HEIDI) model coupled with the Space Weather Modeling Framework (SWMF). This approach provides insight into the role of neutral constituents of Earth’s exosphere in the overall magnetosphere dynamics.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2019

Author dc:creator

• Huang, Yu

Contributors dc:contributor

• Ilie, Raluca

• Space Science, Machine Learning, Decision Tree, Magnetosphere, Ring Current, Geocorona

Statement dc:rights

• Copyright 2019 Yu Huang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/105832

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/105832