Integrating subway checkout data for shared micromobility demand forecasting: A novel deep learning framework

Read full text Summarise with VIRAT
Authors: Linda Belkessa, Mostafa Ameli, Mohsen Ramezani, Mahdi Zargayouna
Cited by: 0
References: 54

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper proposes an integrated shared-micromobility (shared-μM) pickups forecasting method for shared μM systems based on a Multi-Channel Attention Spatio-Temporal Graph Convolutional Network (MC-Att-STGCN) with a custom Weighted Normalized Mean Absolute Error (WNMAE) loss function. The method adopts an infrastructure-aware approach for adjacency estimation and systematically compares four strategies for constructing the time-dependent graph: inverse spatial distance, inverse cycling/walking travel time, Pearson demand correlation, and a fully learnable dual local-global attention-based adjacency. Weather inputs are compressed into a single supervised scalar index using an XGBoost-based aggregation scheme to reduce collinearity while preserving predictive information. Additionally, data-related robustness measures and cross-loss diagnostics (MSE, MAE, RMSE, RRSE, oPNBI) are used to assess forecasting quality under data distribution shifts, presence of outliers, and out-of-sample station scenarios. The proposed framework is applied to New York City and Washington, D.C. data demonstrate the interpretability of the model by inspecting multi-channel calibrated weights of various inputs and the learned adjacency matrix, which extracts infrastructure-consistent communities and multimode interaction patterns between stations. Results show enhanced forecasting capabilities while effectively capturing both morning and evening demand peaks at high-volume bike-sharing stations, and maintaining stable performance across off-peak periods. Moreover, at stations with lower demand, our model exhibits superior performance compared to established methods such as ARIMA, STGCN, GNN-LSTM, ASTGCN , and STAEformer , achieving on average a double-digit percentage reduction in Mean Absolute Error (MAE), and effectively accommodating weekday-weekend distribution shifts and holiday patterns. Furthermore, incorporating weather (W) data through the compressed scalar index and exploiting the μM -PT-W setting of the model yield further reductions in error during adverse meteorological conditions, while the explicit inclusion of public transport (PT) checkouts consistently improves forecasts at multimode hubs. These findings underscore the informative value of PT checkout signals and aggregated weather features for accurate and robust bike-sharing pickup forecasting, and highlight attention-based multimode graphs as an effective architecture for operational decision support in urban shared- μM systems.

Fields of Study & Subjects

Traffic Prediction and Management Techniques Urban Transport and Accessibility Transportation and Mobility Innovations

Publication details

Journal / source
Transportation Research Part C Emerging Technologies
Volume
187
Pages
105650–105650
Publication date
26 March 2026
Language
EN