Spatiotemporal Travel Demand

Spatiotemporal travel demand analysis focuses on understanding and predicting how travel demand varies across locations and time. Current research emphasizes developing sophisticated models, including graph neural networks and convolutional networks, to improve the accuracy and efficiency of these predictions, particularly for emerging transportation modes like shared micromobility and electric vehicles. This work is crucial for optimizing transportation systems, resource allocation (e.g., vehicle rebalancing, charging infrastructure), and urban planning by providing more accurate and reliable forecasts of travel patterns and associated demands. Furthermore, incorporating uncertainty quantification into these models is gaining traction to enhance the robustness and reliability of predictions.