AI Insight
Researchers developed IST-LSTM, a neural network model that forecasts short-term metro passenger flow at individual stations by combining spatial and temporal analysis. The model uses a dual-branch architecture with a Diffusion-Convergence Graph to capture how passengers spread between stations and how stations cluster structurally, while integrating Swin Transformer modules with LSTM networks to better detect both long-range temporal patterns and local variations. Testing on metro data from Nanjing and Hangzhou showed the model reduced prediction errors by approximately 9% compared to existing forecasting methods.
Why it matters
Accurate prediction of metro passenger flows enables transit operators to optimize train scheduling, allocate staff more efficiently, and manage crowding in real-time. The model's improved performance in dense, heterogeneous urban environments could enhance operational planning and passenger experience in major metropolitan transit systems.
Understand the Science
by Yixin Feng, Shangbing Gao, Hao Wang, Anming Bai, Gang Ren, Yuanyuan Wang, Guxue Gao, Jiahuan Ren
Short‑term metro passenger flow forecasting—predicting station‑level inflow and outflow volumes is challenging, mainly due to the complexity of multimodal spatial couplings and the difficulty of modeling long‑range temporal dependencies while retaining local variations. Therefore, this paper proposes an Integrated Spatio-Temporal LSTM (IST-LSTM). IST-LSTM adopts a dual-branch architecture in which a diffusion branch explicitly models OD-driven propagation and a convergence branch captures structural aggregation among stations; these branches are coupled through a Diffusion and Convergence Graph (DCG) that fuses structural links, inter-station distances, and behavior-driven OD diffusion into a unified spatial representation. To strengthen temporal representation, we refine the LSTM gating mechanism by integrating a Swin Transformer module, enabling the model to better represent long-range dependencies while retaining sensitivity to local, fine-grained temporal patterns. To evaluate model generalization under dense and heterogeneous urban conditions, we construct the NJMetro dataset from Nanjing AFC smart-card transaction data, which reflects inner-ring high-density travel dynamics and pronounced spatio-temporal heterogeneity; this dataset is used alongside the public HZMetro dataset. IST-LSTM reduces RMSE by 9.19% on NJMetro relative to GCN-SBULSTM and achieves an average MAE improvement of 9.62% over Graph WaveNet on HZMetro and 8.68% versus LSTM on NJMetro. On HZMetro, it also achieves competitive RMSE performance relative to PB-GRU, with notable advantages at 15- and 30-minute horizons. Overall, the results indicate that the proposed design more effectively captures the coupled spatial and temporal mechanisms underlying metro passenger flow.