Generating population migration flow data from inter-regional relations using graph convolutional network

• Published in: International journal of applied earth observation and geoinformation Vol. 118; p. 103238
• Main Authors: Wang, Yuxia, Yao, Xin, Liu, Yu, Li, Xia
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2023; Elsevier
• Subjects: Flow generation; Graph convolutional network; Inter-regional relation; k-nearest neighbor; Population migration; Flow generation; Population migration; Graph convolutional network; k-nearest neighbor; Inter-regional relation
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2023.103238

Spatial and socioeconomic structures of geographical units produce various inter-regional relations, which impose a direct effect on origin–destination flows. Currently, most flow prediction models only lay emphasis on regional attributes ignoring the inter-regional relations, which limits their abilities to estimate spatial flows more accurately. In this research, we apply the graph convolutional network (GCN) architecture to generate flow data based on inter-regional relations, providing a promising perspective for spatial flow modeling. We develop a relation-to-flow graph convolutional network (R2F-GCN) model to learn the latent representations of regions in an inter-regional relation graph for flow intensity estimation. The relational graph is constructed using the k-nearest neighbor method. We validate the feasibility and effectiveness of our model with experiments based on a mobility dataset of 281 Chinese cities and inter-city relations regarding spatial proximity and transport connectivity. We also discuss the impacts of hyperparameters on the model’s performance. •A relation-to-flow graph convolutional network is proposed for flow generation.•The effectiveness of the model is validated with a real-world mobility dataset.•The impact of key hyperparameters on model performance is analyzed.