Semester of Graduation
Summer 2026
Degree Type
Dissertation
Degree Name
Ph.D in Interdisciplinary Engineering
Department
Department of Electrical and Computer Engineering
Committee Chair/First Advisor
Dr. Mahyar Amirgholy
Second Advisor
Dr. Turaj Ashuri
Third Advisor
Dr. Roneisha Worthy
Fourth Advisor
Dr. Mohammad Tayarani
Abstract
The environmental benefits of electric vehicle (EV) adoption depend on more than replacing internal combustion engine vehicles with electric powertrains. EV adoption reshapes electricity demand, interacts with regional generation mixes, and influences travel behavior and congestion, creating a coupled transportation-energy system in which vehicle and power-plant emissions must be evaluated together. This dissertation develops machine-learning frameworks for predicting energy consumption and emissions from vehicles and power grids under rising EV adoption. The first component forecasts grid emissions from EV charging. Using simulation data from NREL's Cambium database, a Prophet-based time-series framework predicts carbon dioxide, nitrous oxide, and methane emission rates across U.S. energy-sector regions through 2050, capturing long-term trends, seasonality, and scenario-driven variation under multiple generation scenarios. The second component builds an integrated vehicle, traffic, fleet, and power plant emission framework. A feedforward neural network trained on EPA MOVES4 data estimates vehicle energy use and emissions by vehicle type, fuel, age, and speed; state registration data capture fleet heterogeneity; and a Macroscopic Fundamental Diagram model represents network-level traffic dynamics. The framework combines vehicle-side and charging-related power-plant emissions for Atlanta, Los Angeles, New York, and Seattle. Results show that rising EV adoption does not automatically eliminate emissions growth: by 2030, gasoline use and vehicle emissions can still increase under traffic vii growth and mixed-fleet conditions. However, projected grid decarbonization substantially reduces charging-related emissions, demonstrating that electrification is far more effective when paired with cleaner generation, congestion mitigation, and coordinated charging.
Included in
Databases and Information Systems Commons, Data Science Commons, Dynamical Systems Commons, Energy and Utilities Law Commons, Energy Systems Commons, Environmental Engineering Commons, Environmental Law Commons, Environmental Studies Commons, Longitudinal Data Analysis and Time Series Commons, Multi-Vehicle Systems and Air Traffic Control Commons, Navigation, Guidance, Control and Dynamics Commons, Navigation, Guidance, Control, and Dynamics Commons, Oil, Gas, and Energy Commons, Oil, Gas, and Mineral Law Commons, Other Computer Sciences Commons, Other Electrical and Computer Engineering Commons, Other Environmental Sciences Commons, Other Mathematics Commons, Power and Energy Commons, Probability Commons, Software Engineering Commons, Statistical Theory Commons, Sustainability Commons, Transportation and Mobility Management Commons, Transportation Engineering Commons, Transportation Law Commons, Transport Phenomena Commons
Comments