Doctoral Dissertation Research: Electric Vehicle Users' Charging Behaviors: A GeoAI Approach

This project examines the charging of electric vehicles from a geographical perspective. Using locational data from mobile phones, the researchers implement machine learning algorithms to study how drivers of electric vehicles select locations for charging their vehicles. These methods permit the identification of drivers’ preferences for charging locations, including the times when these charging stations are used. In turn, these findings permit the identification of geographical locations where new charging stations would be valuable. The results of this project can be used by regional planners to deduce promising locations for new infrastructure, and the methods used in this work can be extended to other planning contexts in which the analysis of large datasets is helpful. The project extends the application of artificial intelligence methods in the geographical sciences and provides valuable research training for a graduate student. This study develops a novel methodological approach to studying the decisions made by users of electric vehicles. Contributing to the field of GIScience, the researchers advance geospatial methods and statistical analyses to model the spatiotemporal patterns of charging electric vehicles. The insights from this study contribute to the efficiency, sustainability, and optimization of charging locations for electric vehicles that reduce the need for detours while minimizing wait times. The study advances a new optimization metric that balances the geographical availability of charging stations and the anticipated demand, and this metric can be implemented in analogous infrastructural contexts. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.