Graduation Semester and Year
Spring 2024
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Physics and Applied Physics
Department
Physics
First Advisor
Yue Deng
Second Advisor
Mingwu Jin
Abstract
Machine learning techniques, particularly deep learning techniques, have been vigorously pursued to tackle space physics problems and achieved some impressive results recently. The growth of deep learning technologies in different domains enables innovative solutions to those problems compared to conventional methods. Filling data gaps in instrumental observations is among the demanding issues, which benefits space physicists to study ionospheric phenomena with complete data coverage. Global total electron content (TEC) and regional ionospheric electron density (Ne) are among important physical parameters in ionospheric studies. Due to the limited coverage of global navigation satellite system (GNSS) ground receivers and sporadic operations of the Millstone Hill incoherent scatter radar (ISR), the global TEC maps and regional Ne observations suffer huge amount of data gaps. In this dissertation, we utilize the advanced deep learning methods, generative adversarial networks (GANs) and neural architectural search (NAS), to fill the data gaps in TEC maps and Ne patterns. We have conducted comprehensive experiments to demonstrate their superior performances over traditional methods. Through these studies, it becomes increasingly evident that the great potential of deep learning will play a key role in future research of ionosphere and the broader realm of space physics.
Keywords
Deep Learning, Ionosphere, Total Electron Content, Electron Density
Disciplines
Physics
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Pan, Yang, "DEEP LEARNING APPLICATIONS ON IONOSPHERIC STUDIES" (2024). Physics Dissertations. 1.
https://mavmatrix.uta.edu/physics_dissertations/1