This $174,734 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) will support research at South Dakota State University (SDSU) to develop advanced analytics and machine learning techniques for predicting the spatiotemporal impacts of traffic incidents on transportation systems.
The key objectives of this 2-year project are to: 1) create novel multimodal representation learning approaches combining machine learning and graph mining to learn text-enriched embeddings of traffic events from heterogeneous data sources; 2) develop spatiotemporal data mining and transformer-based graph neural network methods to detect transportation events and analyze their cascading impacts on transportation networks; and 3) develop a physics-informed machine learning solution to model and forecast the cascading impacts of traffic incidents using the Korteweg-de Vries (KdV) equation. These advancements are expected to significantly contribute to the fields of explainable graph mining, physics-informed machine learning, and spatiotemporal event analysis. No subawards are planned under this grant.
Generated 3/4/25, 6:29 AM