Fine-grained crowd distribution forecasting with multi-order spatial interactions using mobile phone data. (November 2022)

• Record Type: Journal Article
• Authors: Li, Mingxiao; Gao, Song; Qiu, Peiyuan; Tu, Wei; Lu, Feng; Zhao, Tianhong; Li, Qingquan
• Is Part Of: Transportation research. Volume 144(2022)
• Publication Date: 2022-11
• Subjects: Crowd distribution forecasting -- Multi-order spatial interaction -- Embedding learning -- Trajectory enhancement -- Human mobility; Transportation -- Periodicals; Transportation -- Technological innovations -- Periodicals; 388.011
• DOI: 10.1016/j.trc.2022.103908
• Languages: English
• ISSNs: 0968-090X

Abstract

Highlights: A hybrid graph-based deep learning model was constructed for crowd distribution forecasting. A trajectory enhancement algorithm was applied to improve interaction characterization. The multi-order spatial interactions among non-adjacent spatial units were highlighted. The outperformance of the proposed method was demonstrated with a real-world dataset. Abstract: Fine-grained crowd distribution forecasting benefits smart transportation operations and management, such as public transport dispatch, traffic demand prediction, and transport emergency response. Considering the co-evolutionary patterns of crowd distribution, the interactions among places are essential for modelling crowd distribution variations. However, two issues remain. First, the lack of sampling design in passive big data acquisition makes the spatial interaction characterizations of less crowded places insufficient. Second, the multi-order spatial interactions among places can help forecasting crowd distribution but are rarely considered in the existing literature. To address these issues, a novel crowd distribution forecasting method with multi-order spatial interactions was proposed. In particular, a weighted random walk algorithm was applied to generate simulated trajectories for improving the interaction characterizations derived from sparse mobile phone data. The multi-order spatial interactions among contextual non-adjacent places were modelled with an embedding learning technique. The future crowd distribution was forecasted via a graph-based deep neural network. The proposed method was verified using a real-world mobile phone dataset, and the results showed that both the multi-order spatial interactions and the trajectory data enhancement algorithm helped improve the crowd distribution forecasting performance. The proposed method can be utilized for capturing fine-grained crowd distribution, which supports various applications such as intelligent transportation management and public health decision making.