Title: Employing Machine Learning Techniques to Increase the Quality of Ionospheric Modeling

Date: July 9, 2025

Time: 2:00 PM EDT

Location: Van Leer 218

Virtual: https://gatech.zoom.us/j/95145365349?pwd=naXbcJeBkUbUHERizobilOwJKmNXok.1

Meeting ID: 951 4536 5349

Passcode: 709575

Liam Smith

Machine Learning PhD Student

School of Electrical and Computer Engineering
Georgia Institute of Technology

Committee

1 Dr. Morris Cohen (Advisor)

School of Electrical and Computer Engineering

Georgia Institute of Technology

2 Dr. David Anderson

School of Electrical and Computer Engineering

Georgia Institute of Technology

3 Dr. Mark Davenport

School of Electrical and Computer Engineering

Georgia Institute of Technology

4 Dr. Justin Romberg

School of Electrical and Computer Engineering

Georgia Institute of Technology

5 Dr. Sven Simon

School of Earth and Atmospheric Sciences

Georgia Institute of Technology

Abstract

Wireless communications are impacted by the ionosphere, which is the charged part of the upper atmosphere. This ionization affects the signal paths of communications, with some signals reflecting and others passing through. Understanding the state of the ionosphere, specifically the electron density, gives insight into how these signal paths are affected. Thus, knowing the electron density of the ionosphere is quite desirable. Because the ionosphere is difficult to densely measure, observations are sparse, and models are needed to complete the data. This work investigates modeling the ionosphere with Machine Learning (ML) and using various techniques to enable the usage of additional data types. Specifically, this work details the use of temporal architectures to include fine-grained solar information and missing-compliant networks to deal with sparse data.