"PeMS"

"he California Performance Measurement System (PeMS) provides one of the most widely used traffic datasets for transportation research, offering continuous measurements of traffic flow, speed, and occupancy collected by loop detectors installed throughout the California state highway network. This dataset focuses on District 4 (San Francisco Bay Area), where traffic data are recorded at 5-minute intervals across multiple sensor stations.This integrated dataset provides a valuable benchmark for advancing research in spatiotemporal forecasting, intelligent transportation systems, traffic management, and urban mobility analysis. It is particularly suitable for the development of deep learning models such as graph neural networks, recurrent neural networks, and transformer-based architectures, where capturing nonlinear temporal dependencies and external influences is essential."