*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Topside Ionospheric Modeling Using Machine Learning
Committee:
Dr. Cohen, Advisor
Dr. Steffes, Chair
Dr. Simon
Abstract: The objective of the proposed research is to create a reliable forecast of the electron density of the topside ionosphere, focusing on the altitudes of Low Earth Orbit satellites. Prior work used data from the Defense Meteorological Satellite Program (DMSP), a collection of 19 satellites that have been polar orbiting the Earth for various lengths of times, fully covering 1982 to the present. Using this data, a neural network (NN) was developed and trained on two solar cycles worth of data (113 satellite-years), along with global drivers and indices such as F10.7, interplanetary magnetic field (IMF), and Kp to generate an electron density prediction. The NN model was tested on 6 years of subsequent data (26 satellite-years), and a correlation coefficient of 0.87 was obtained. Once trained, the model can predict topside electron density at any location specified by latitude and longitude given current/recent geomagnetic conditions. Comparing our current model to the International Reference Ionosphere (IRI) model (Bilitza, Reinisch, et al. 2006; Bilitza 2018) using data from the DEMETER satellite, we find that our model works better at low to mid-latitudes, and for quiet and moderately disturbed geomagnetic conditions even when making electron density predictions outside of its trained altitude range. Proposed work includes improvement of this model via modified training, testing, and validation datasets, ensembling the NN model with the IRI and E-CHAIM, and ultimately creating a forecaster by inputting forecasts of the NN model's inputs.
