{"675586":{"#nid":"675586","#data":{"type":"event","title":"Ph.D. Dissertation Defense - Shweta Dutta","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E\u003Cem\u003E:\u0026nbsp; Topside Ionospheric Modeling using Machine Learning\u003C\/em\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Morris Cohen, ECE, Chair, Advisor\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Paul Steffes, ECE\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Zsolt Kira, IC\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Michael Peterson, GTRI\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Andrew Peterson, ECE\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EThe topside ionosphere is the gateway between the lower ionosphere and the plasmasphere\/magnetosphere above, and\u003Cbr\u003Eis critical to the function of GPS\/radio communications, satellites, and the power grid. Existing models of the topside\u003Cbr\u003Eionosphere are empirical or use empirical model as input, and not as resiliant to extreme conditions, like the effects of\u003Cbr\u003Esolar storms. In this thesis, I investigate the use of machine learning to develop a model of the topside ionosphere that is\u003Cbr\u003Ebuilt on in-situ satellite data and is better suited to accurately modeling the ionosphere in extreme conditions, develop\u003Cbr\u003Eextensions of the model by designing a hybrid model that blends empirical models with machine learning allowing for the\u003Cbr\u003Eadvantages of both types of models to be combined, provide information about relative model importance within a hybrid\u003Cbr\u003Emodel, and use the improved topside models to improve total electron content modeling. I begin by investigating the\u003Cbr\u003Eintersection between modeling the Earth\u0027s ionosphere and using machine learning to model systems in Earth\u0027s upper\u003Cbr\u003Eatmosphere, which illustrates the need for a better topside ionospheric model. This leads into the development of a neural\u003Cbr\u003Enetwork model of the topside ionosphere, including the feature selection process and performance analysis of this purely\u003Cbr\u003Emachine learning based model. To expand the model domain, I apply stacked generalization to combine the developed\u003Cbr\u003Emachine learning model with existing empirical models, specifically the International Reference Ionosphere and E-CHAIM,\u003Cbr\u003Eand determine model importance within the stacked generalization model using Shapley values. Finally, I analyze the use\u003Cbr\u003Eof topside electron density predictions to improve total electron content modeling, and provide better TEC predictions.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Topside Ionospheric Modeling using Machine Learning "}],"uid":"28475","created_gmt":"2024-07-24 22:14:53","changed_gmt":"2024-07-24 22:15:55","author":"Daniela Staiculescu","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-07-29T14:00:00-04:00","event_time_end":"2024-07-29T16:00:00-04:00","event_time_end_last":"2024-07-29T16:00:00-04:00","gmt_time_start":"2024-07-29 18:00:00","gmt_time_end":"2024-07-29 20:00:00","gmt_time_end_last":"2024-07-29 20:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Room W225, Van Leer","extras":[],"groups":[{"id":"434381","name":"ECE Ph.D. Dissertation Defenses"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"},{"id":"1808","name":"graduate students"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}