Enhancing urban flow prediction via mutual reinforcement with multi-scale regional information

• Published in: Neural networks 2025-02, Vol.182, p.106900, Article 106900
• Main Authors: Zhang, Xu, Cao, Mengxin, Gong, Yongshun, Wu, Xiaoming, Dong, Xiangjun, Guo, Ying, Zhao, Long, Zhang, Chengqi
• Format: Article
• Language: English
• Subjects: Algorithms; Humans; Multi-scale region information; Mutual reinforcement; Neural networks; Neural Networks, Computer; Spatial–temporal systems; Transportation; Urban flow prediction; Urban Renewal
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2024.106900

Intelligent Transportation Systems (ITS) are essential for modern urban development, with urban flow prediction being a key component. Accurate flow prediction optimizes routes and resource allocation, benefiting residents, businesses, and the environment. However, few methods address the spatial–temporal heterogeneity of urban flows. Existing methods typically capture spatial features solely from urban flows, but spatial feature sensitivity becomes a bottleneck when dealing with small or noisy datasets. To address this issue, we propose a method for urban flow prediction via mutual reinforcement with multi-scale regional information (MR-UFP). Firstly, we employ spatial–temporal random masking and spatial–temporal contrastive learning pre-training to directly mine spatial–temporal heterogeneity from historical flow data. Secondly, we transform the task of spatial feature extraction and embedding for urban flow prediction into a mutual reinforcement task by multi-scale region classification auxiliary task. The adaptive environment fusion module and real-time graph processing dynamically correlate regional and environmental features during flow prediction. To balance the mutual reinforcement of the two tasks, we design a joint loss function to optimize feature embedding and feedback correction, ensuring robust and accurate urban flow prediction. Extensive experiments on two real-world datasets demonstrate that MR-UFP outperforms baseline models, showcasing its robustness and effectiveness even with minimal data. •Mutual reinforcement with multi-scale regional information for urban flow prediction.•Proposed multi-scale region classification with manual annotations for spatial feature extraction.•Adaptive environment fusion and real-time adjacency matrix enhance spatial features.•Joint loss function refines spatial feature representation and optimizes prediction results.