Project Grant 2409847

This National Science Foundation (NSF) project grant, under the Engineering program (CFDA 47.041), provides $432,572 in funding to Drexel University to support research that investigates the impacts of deep learning on decision-making for transit systems. The project aims to develop a new deep learning paradigm that directly integrates decision models into the model design, with a focus on improving transit system applications such as timetable design and bus motion control. The research seeks to help transit decision-makers understand the impacts of deep learning on their outcomes and offer a framework for developing deep learning models with verifiable decision quality, even in adversarial scenarios. The project will also provide interdisciplinary education and research training opportunities for students, including efforts to engage underrepresented minority participants. The award period spans from October 1, 2024 to September 30, 2027.