Correlation-based feature selection and parallel spatiotemporal networks for efficient passenger flow forecasting in metro systems
Document Type
Journal Article
Publication Date
2026
Subject Area
place - asia, place - urban, mode - subway/metro, ridership - forecasting
Keywords
Traffic forecasting, Deep learning, Spatiotemporal dependence, Feature extraction, Metro domain knowledge
Abstract
This paper presents a novel framework for predicting metro passenger flow that is both interpretable and computationally efficient. The proposed method first uses a correlation-based spatiotemporal feature selection strategy (Cor-STFS) to identify the optimal input scheme for the prediction model, effectively reducing unnecessary interference. The framework then introduces a new multivariate passenger flow prediction architecture called STA-PTCN-BiGRU, which combines a spatiotemporal attention (STA) mechanism, parallel temporal convolutional networks (PTCN), and bidirectional gated recurrent units (BiGRU) to capture the dynamic internal patterns of passenger flow. By utilising parallel computing, this architecture significantly reduces resource consumption. The effectiveness of the proposed approach is evaluated using four datasets from the Shanghai Metro. Experimental results show that the new method outperforms baseline approaches in terms of root mean square error (RMSE), mean absolute error (MAE), and symmetric mean absolute percentage error (SMAPE), achieving average reductions of 9.98%, 8.08%, and 13.29% in these metrics, respectively.
Rights
Permission to publish the abstract has been given by Taylor&Francis, copyright remains with them.
Recommended Citation
Xiu, C., Zhan, S., Pan, J., Peng, Q., Lin, Z., & Wong, S. C. (2026). Correlation-based feature selection and parallel spatiotemporal networks for efficient passenger flow forecasting in metro systems. Transportmetrica A: Transport Science, 22(1), 1.
