LAUSR

Origin-Destination (OD) flow contains the information of direction and volume of population mobility between different regions in a city, having significant value in public transportation resource allocation. Nevertheless, OD flow data is difficult to be collected due to high cost and privacy concerns. Alternatively, population distribution data is more easily accessible and less privacy-sensitive, and its variation can reflect the human mobility flow in urban regions. Motivated by this, in this paper, we explore population distribution to infer OD flows, which is called pop2flow (population distribution to OD flows) problem. Compared to the conventional OD forecasting problem by using the historical OD matrix, pop2flow is more challenging because the population distribution carries much less information. In order to solve the pop2flow problem, we proposed a model, Graph-based Spatial-temporal Embedding with Dynamic Fusion (GSTE-DF). Specifically, GSTE-DF is composed of two parts: node embedding learning and flow prediction. The node embedding learning part captures the dynamic spatial-temporal features of population distribution into each node's embedding. The flow prediction part adopts the learned embeddings and POI (points of interesting) distribution of every two regions to infer the population interaction between them. By conducting extensive experiments on real-world datasets collected in Beijing and New York City, we demonstrate the superiority of GSTE-DF compared to state-of-the-art baselines.