EPSCoR Research Fellows: NSF: Transforming Transportation Planning in EPSCoR Jurisdictions through AI-Enhanced Mobility Data and Foundational Modeling

This Research Infrastructure Improvement (RII) EPSCoR Research Fellows project provides a fellowship to an Assistant professor at the University of Louisville. This work is conducted in collaboration with researchers at Northeastern University. Through the fellowship, the PI will develop advanced methods for using large-scale mobility data and artificial intelligence to improve transportation demand modeling and planning in data-limited regions, as limited travel data and modeling resources constrain the ability to understand changing travel behavior and anticipate transportation demand in EPSCoR jurisdictions. The project will develop methods to enhance emerging mobility data, learn transferable patterns of human travel behavior, and adapt these methods for transportation planning applications by integrating transportation engineering, data science, and artificial intelligence. This project will strengthen research capacity at the University of Louisville, expand workforce training in data-intensive transportation research and artificial intelligence, and support more informed and resilient transportation planning in EPSCoR jurisdictions. The project will establish a scalable data-to-model-to-application framework for artificial intelligence-driven human mobility modeling. The intellectual contribution is the development of transferable methods transforming sparse mobility data into behaviorally enriched information and informing resilient transportation planning. The research will integrate mobility, travel survey, and geographic data to infer travel behavior information, reconstruct incomplete trajectories, and address sampling biases. These enhanced data will support a foundation mobility model by integrating spatio-temporal representation and scale through self-supervised training on large mobility datasets. Transfer learning will adapt and validate the model in Louisville and demonstrate its use for transportation demand analysis and planning. Access to longitudinal mobility data, and high-performance computing at Northeastern University will advance the PI’s expertise and establish reproducible computational workflows at the home institution. The project will further expand graduate training, strengthen interdisciplinary partnerships, and build sustained capacity for data-intensive transportation research and planning. This project is supported by the EPSCoR Research Infrastructure Improvement Program: EPSCoR Research Fellows (ERF). The ERF program supports early- and mid-career investigators in eligible jurisdictions to develop collaborations at the nation’s private, government, or academic research institutions. 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.