MADENet: Explainable AI-Driven Bike-Sharing Demand Forecasting for Sustainable Urban Mobility

Jianbo Huang; Yanbin Zheng; Lihua Lan; Jia Chen

doi:10.62177/jaet.v2i4.662

Authors

Jianbo Huang Guilin University of Technology
Yanbin Zheng Guilin University of Technology
Lihua Lan Guilin University of Technology
Jia Chen Guilin University of Technology

DOI:

https://doi.org/10.62177/jaet.v2i4.662

Keywords:

Bike-Sharing, Explainable AI, Smart City, Sustainable Transportation

Abstract

With rapid urbanization and increasing motorization, bike-sharing systems have emerged as sustainable solutions for urban "last-mile" connectivity. However, existing demand forecasting approaches face a critical trade-off between predictive accuracy and operational interpretability, limiting their practical deployment in municipal deci-sion-making contexts where both reliable predictions and transparent insights are essen-tial. The study proposes MADENet, a novel neural architecture that systematically ad-dresses this accuracy-interpretability challenge. The framework integrates three key inno-vations: multi-head attention mechanisms to dynamically capture cross-regional demand dependencies and temporal periodicity patterns; adaptive dropout with early-stopping regularization to mitigate overfitting in high-dimensional spatio-temporal scenarios; and multilayer perceptron components to model complex nonlinear interactions between het-erogeneous external factors and urban mobility patterns.Experimental evaluation demon-strates MADENet's superior performance, achieving 95.1% prediction accuracy (R²=0.9515, MAE=0.2320) and outperforming 15 baseline algorithms with MAE improvements rang-ing from 7.7% to 70% across different algorithmic paradigms. Embedded SHAP and LIME explainable AI frameworks systematically identify hour-of-day, temperature, and humid-ity as dominant spatio-temporal drivers while quantifying their nonlinear interactions with demand patterns.These innovations provide transparent operational protocols for station layout optimization, dynamic fleet rebalancing, and evidence-based policy formu-lation, ultimately advancing data-driven governance of sustainable urban mobility sys-tems through actionable insights that bridge algorithmic predictions with practical urban planning requirements.

Downloads

Download data is not yet available.

References

Afsari, M., Dastmard, M., Bresciani Miristice, L. M., & Gentile, G. (2024). Utilizing P-median and Machine Learning for Bike-Sharing Demand Prediction. 2024 IEEE International Conference on Environment and Electrical Engineering and 2024 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe), 1–5. https://doi.org/10.1109/EEEIC/ICPSEurope61470.2024.10751398

Andor, M. A., Gerster, A., Gillingham, K. T., & Horvath, M. (2020). Running a car costs much more than people think—Stalling the uptake of green travel. Nature, 580(7804), 453–455. https://doi.org/10.1038/d41586-020-01118-w

Biswas, Md. E., Hossain, Md. D., Huh, E.-N., & Sultana, T. (2025). Spatiotemporal Data-Driven Hourly Bike-Sharing Demand Prediction Using ApexBoost Regression. International Journal of Data Science and Analytics. https://doi.org/10.1007/s41060-025-00820-0

Chen, P., Hsieh, H., Su, K., Sigalingging, X. K., Chen, Y., & Leu, J. (2020). Predicting station level demand in a bike‐sharing system using recurrent neural networks. IET Intelligent Transport Systems, 14(6), 554–561. https://doi.org/10.1049/iet-its.2019.0007

Cheng, C., & Yue, W. (2024). Construction of a Green and Low-Carbon Travel Order Prediction Model Based on Shared Bicycle Big Data. International Journal of Computational Intelligence Systems, 17(1), 130. https://doi.org/10.1007/s44196-024-00519-3

Chengula, T. J., Mwakalonge, J., Comert, G., Sulle, M., Siuhi, S., & Osei, E. (2024). Enhancing advanced driver assistance systems through explainable artificial intelligence for driver anomaly detection. Machine Learning with Applications, 17, 100580. https://doi.org/10.1016/j.mlwa.2024.100580

Collini, E., Nesi, P., & Pantaleo, G. (2021). Deep Learning for Short-Term Prediction of Available Bikes on Bike-Sharing Stations. IEEE Access, 9, 124337–124347. https://doi.org/10.1109/ACCESS.2021.3110794

E, S. V., Park, J., & Cho, Y. (2020). Using data mining techniques for bike sharing demand prediction in metropolitan city. Computer Communications, 153, 353–366. https://doi.org/10.1016/j.comcom.2020.02.007

Feng, J., Liu, H., Zhou, J., & Zhou, Y. (2024). A Spatial-Temporal Aggregated Graph Neural Network for Docked Bike-sharing Demand Forecasting. ACM Transactions on Knowledge Discovery from Data, 18(9), 1–27. https://doi.org/10.1145/3690388

Galatoulas, N.-F., Genikomsakis, K. N., & Ioakimidis, C. S. (2020). Spatio-Temporal Trends of E-Bike Sharing System Deployment: A Review in Europe, North America and Asia. Sustainability, 12(11), 4611. https://doi.org/10.3390/su12114611

Gao, C., & Chen, Y. (2022). Using Machine Learning Methods to Predict Demand for Bike Sharing. In J. L. Stienmetz, B. Ferrer-Rosell, & D. Massimo (Eds.), Information and Communication Technologies in Tourism 2022 (pp. 282–296). Springer International Publishing. https://doi.org/10.1007/978-3-030-94751-4_25

Giner Fabregat, G., Fonseca I Casas, P., & Rivero Martínez, A. (2025). Intelligent Optimization of Bike-Sharing Systems: Predictive Models and Algorithms for Equitable Bicycle Distribution in Barcelona. Sustainability, 17(10), 4316. https://doi.org/10.3390/su17104316

Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., & Yang, G.-Z. (2019). XAI—Explainable artificial intelligence. Science Robotics, 4(37), eaay7120. https://doi.org/10.1126/scirobotics.aay7120

Guo, H., Li, K., & Rou, Y. (2024). Optimized Demand Forecasting for Bike-Sharing Stations Through Multi-Method Fusion and Gated Graph Convolutional Neural Networks. IEEE Access, 12, 174017–174027. https://doi.org/10.1109/ACCESS.2024.3501572

Guo, H., Zhao, S., Ren, Y., Li, J., & Xu, S. (2025). An XGBoost-Based Three-Stage Prediction Approach for True User Demand of Bike-Sharing Systems Based on Spatio-Temporal Analysis. IEEE Transactions on Intelligent Transportation Systems, 1–12. https://doi.org/10.1109/TITS.2025.3586747

Hu, Y., Sun, Z., Li, W., & Pei, L. (2022). Forecasting public bicycle rental demand using an optimized eXtreme Gradient Boosting model. Journal of Intelligent & Fuzzy Systems, 42(3), 1783–1801. https://doi.org/10.3233/JIFS-211202

Lee, Y., Son, H., Ahn, J., & Cho, S. (2024). Bike-sharing Demand Prediction based on Artificial Intelligence Algorithm Using Weather Data. 2024 IEEE International Conference on Consumer Electronics (ICCE), 1–6. https://doi.org/10.1109/ICCE59016.2024.10444462

Li, X., Xu, Y., Chen, Q., Wang, L., Zhang, X., & Shi, W. (2022). Short-Term Forecast of Bicycle Usage in Bike Sharing Systems: A Spatial-Temporal Memory Network. IEEE Transactions on Intelligent Transportation Systems, 23(8), 10923–10934. https://doi.org/10.1109/TITS.2021.3097240

Li, X., Xu, Y., Zhang, X., Shi, W., Yue, Y., & Li, Q. (2023). Improving short-term bike sharing demand forecast through an irregular convolutional neural network. Transportation Research Part C: Emerging Technologies, 147, 103984. https://doi.org/10.1016/j.trc.2022.103984

Li, Y., & Zheng, Y. (2020). Citywide Bike Usage Prediction in a Bike-Sharing System. IEEE Transactions on Knowledge and Data Engineering, 32(6), 1079–1091. https://doi.org/10.1109/TKDE.2019.2898831

Li, Y., Zhu, Z., Kong, D., Xu, M., & Zhao, Y. (2019). Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 1004–1011. https://doi.org/10.1609/aaai.v33i01.33011004

Liang, Y., Ding, F., Huang, G., & Zhao, Z. (2023). Deep trip generation with graph neural networks for bike sharing system expansion. Transportation Research Part C: Emerging Technologies, 154, 104241. https://doi.org/10.1016/j.trc.2023.104241

Liang, Y., Huang, G., & Zhao, Z. (2024). Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction Using Domain-Adversarial Graph Neural Networks. IEEE Transactions on Intelligent Transportation Systems, 25(5), 3642–3653. https://doi.org/10.1109/TITS.2023.3322717

Lim, H., Chung, K., & Lee, S. (2022). Probabilistic Forecasting for Demand of a Bike-Sharing Service Using a Deep-Learning Approach. Sustainability, 14(23), 15889. https://doi.org/10.3390/su142315889

Lin, H., He, Y., Li, S., & Liu, Y. (2024). Insights into Travel Pattern Analysis and Demand Prediction: A Data-Driven Approach in Bike-Sharing Systems. Journal of Transportation Engineering, Part A: Systems, 150(2), 04023132. https://doi.org/10.1061/JTEPBS.TEENG-8137

Pribadi, A. P., Rauf, A. U., Rahman, Y. M. R., & Haq, Z. F. (2025). Air Quality and Urban Sustainable Development- Current Issues and Future Directions. In J. A. Parray, N. Shameem, & A. K. Haghi (Eds.), Sustainable Urban Environment and Waste Management (pp. 23–51). Springer Nature Singapore. https://doi.org/10.1007/978-981-96-1140-9_2

Qian, H., Wang, J., Chen, Y., Zheng, S., & Wei, Z. (2025). CGA-STNet: A dockless shared bicycle demand prediction model considering multiple spatial features and time periodicity. Expert Systems with Applications, 265, 126100. https://doi.org/10.1016/j.eswa.2024.126100

Roscher, R., Bohn, B., Duarte, M. F., & Garcke, J. (2020). Explainable Machine Learning for Scientific Insights and Discoveries. IEEE Access, 8, 42200–42216. https://doi.org/10.1109/ACCESS.2020.2976199

Sajid, M., Midhun, V., Zakkariya, K. A., Surira, M. D., & Vishnu, K. P. (2023). Pedaling towards sustainability: A mixed-method study of the drivers and barriers to bike-sharing adoption. Management of Environmental Quality: An International Journal, 34(6), 1580–1606. https://doi.org/10.1108/MEQ-12-2022-0343

Schnieder, M. (2023). Ebike Sharing vs. Bike Sharing: Demand Prediction Using Deep Neural Networks and Random Forests. Sustainability, 15(18), 13898. https://doi.org/10.3390/su151813898

Shi, Y., Zhang, L., Lu, S., & Liu, Q. (2023). Short-Term Demand Prediction of Shared Bikes Based on LSTM Network. Electronics, 12(6), 1381. https://doi.org/10.3390/electronics12061381

Shi, Z., Jiang, Z., Xu, M., Zhou, Y., & Zhu, Z. (2025). Enhancing Hybrid Bike-Sharing Systems Through Long-Term Inventory Management: A Generative-Model-Informed Reinforcement Learning Approach. IEEE Transactions on Computational Social Systems, 1–13. https://doi.org/10.1109/TCSS.2025.3557911

Wang, T., Hu, S., & Jiang, Y. (2021). Predicting shared-car use and examining nonlinear effects using gradient boosting regression trees. International Journal of Sustainable Transportation, 15(12), 893–907. https://doi.org/10.1080/15568318.2020.1827316

Wang, Z., & Ren, F. (2025). Developing a decision support system for sustainable urban planning using machine learning-based scenario modeling. Scientific Reports, 15(1), 13210. https://doi.org/10.1038/s41598-025-90057-5

Wang, Z., Yu, D., Zheng, X., Meng, F., & Wu, X. (2025). A Model-Data Dual-Driven Approach for Predicting Shared Bike Flow near Metro Stations. Sustainability, 17(3), 1032. https://doi.org/10.3390/su17031032

Wei, X., Ren, Y., Shen, L., & Shu, T. (2022). Exploring the spatiotemporal pattern of traffic congestion performance of large cities in China: A real-time data based investigation. Environmental Impact Assessment Review, 95, 106808. https://doi.org/10.1016/j.eiar.2022.106808

Xiang, Z., Zeng, F., Liu, L., Wu, J., Mumtaz, S., & Leung, V. C. M. (2025). Bike-Sharing Demand Prediction Based on Dynamic Time Warping and Spatio-Temporal Graph Attention Network. IEEE Transactions on Intelligent Transportation Systems, 1–15. https://doi.org/10.1109/TITS.2025.3570009

Xiao, G., Wang, R., Zhang, C., & Ni, A. (2021). Demand prediction for a public bike sharing program based on spatio-temporal graph convolutional networks. Multimedia Tools and Applications, 80(15), 22907–22925. https://doi.org/10.1007/s11042-020-08803-y

Xu, F., Uszkoreit, H., Du, Y., Fan, W., Zhao, D., & Zhu, J. (2019). Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges. In J. Tang, M.-Y. Kan, D. Zhao, S. Li, & H. Zan (Eds.), Natural Language Processing and Chinese Computing (Vol. 11839, pp. 563–574). Springer International Publishing. https://doi.org/10.1007/978-3-030-32236-6_51

Xu, M., Liu, H., & Yang, H. (2020). A Deep Learning Based Multi-Block Hybrid Model for Bike-Sharing Supply-Demand Prediction. IEEE Access, 8, 85826–85838. https://doi.org/10.1109/ACCESS.2020.2987934

Yu, L., Feng, T., Li, T., & Cheng, L. (2023). Demand Prediction and Optimal Allocation of Shared Bikes Around Urban Rail Transit Stations. Urban Rail Transit, 9(1), 57–71. https://doi.org/10.1007/s40864-022-00183-w

Zhu, B., Hu, S., Kaparias, I., Zhou, W., Ochieng, W., & Lee, D.-H. (2024). Revealing the driving factors and mobility patterns of bike-sharing commuting demands for integrated public transport systems. Sustainable Cities and Society, 104, 105323. https://doi.org/10.1016/j.scs.2024.105323