Smart City Gnosys

Smart city article details

Title	Interpretable Bike-Sharing Activity Prediction With A Temporal Fusion Transformer To Unveil Influential Factors: A Case Study In Hamburg, Germany
ID_Doc	33149
Authors	Rühmann S.; Leible S.; Lewandowski T.
Year	2024
Published	Sustainability (Switzerland) , 16, 8
DOI	http://dx.doi.org/10.3390/su16083230
Abstract	Bike-sharing systems (BSS) have emerged as an increasingly important form of transportation in smart cities, playing a pivotal role in the evolving landscape of urban mobility. As cities worldwide strive to promote sustainable and efficient transportation options, BSS offer a flexible, eco-friendly alternative that complements traditional public transport systems. These systems, however, are complex and influenced by a myriad of endogenous and exogenous factors. This complexity poses challenges in predicting BSS activity and optimizing its usage and effectiveness. This study delves into the dynamics of the BSS in Hamburg, Germany, focusing on system stability and activity prediction. We propose an interpretable attention-based Temporal Fusion Transformer (TFT) model and compare its performance with the state-of-the-art Long Short-Term Memory (LSTM) model. The proposed TFT model outperforms the LSTM model with a 36.8% improvement in RMSE and overcomes current black-box models via interpretability. Via detailed analysis, key factors influencing bike-sharing activity, especially in terms of temporal and spatial contexts, are identified, examined, and evaluated. Based on the results, we propose interventions and a deployed TFT model that can improve the effectiveness of BSS. This research contributes to the evolving field of sustainable urban mobility via data analysis for data-informed decision-making. © 2024 by the authors.
Author Keywords	bike-sharing activity; bike-sharing system; demand prediction; Long Short-Term Memory; machine learning; Temporal Fusion Transformer

Similar Articles

Id	Similarity	Authors	Title	Published
26705	0.896	Avignone A.; Napolitano D.; Cagliero L.; Chiusano S.	Flowcasting: A Dynamic Machine Learning Based Dashboard For Bike-Sharing System Management	18th IEEE International Conference on Application of Information and Communication Technologies, AICT 2024 (2024)
20781	0.892	Ali A.; Salah A.; Bekhit M.; Fathalla A.	Divide-And-Train: A New Approach To Improve The Predictive Tasks Of Bike-Sharing Systems	Mathematical Biosciences and Engineering, 21, 7 (2024)
29019	0.886	Yang, JJ; Guo, BZ; Wang, ZH; Ma, YL	Hierarchical Prediction Based On Network-Representation-Learning-Enhanced Clustering For Bike-Sharing System In Smart City	IEEE INTERNET OF THINGS JOURNAL, 8, 8 (2021)
35054	0.884	Manai M.; Sellami B.; Yahia S.B.	Leveraging Data For Better Bike Sharing: A Methodology For Terminal Availability Prediction	Procedia Computer Science, 246, C (2024)
33156	0.88	Onen S.; Ggaliwango M.; Mugabi S.; Nabende J.	Interpretable Machine Learning For Intelligent Transportation In Bike-Sharing	2023 2nd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2023 (2023)
9501	0.879	Roussel C.; Rolwes A.; Böhm K.	Analyzing Geospatial Key Factors And Predicting Bike Activity In Hamburg	Lecture Notes on Data Engineering and Communications Technologies, 143 (2022)
24000	0.877	Subramanian M.; Cho J.; Veerappampalayam Easwaramoorthy S.; Murugesan A.; Chinnasamy R.	Enhancing Sustainable Transportation: Ai-Driven Bike Demand Forecasting In Smart Cities	Sustainability (Switzerland), 15, 18 (2023)
9519	0.877	Cuong D.V.; Ngo V.M.; Cappellari P.; Roantree M.	Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling	IEEE Open Journal of Intelligent Transportation Systems, 5 (2024)
52829	0.875	Chai J.; Song J.; Fan H.; Xu Y.; Zhang L.; Guo B.; Xu Y.	St-Bikes: Predicting Travel-Behaviors Of Sharing-Bikes Exploiting Urban Big Data	IEEE Transactions on Intelligent Transportation Systems, 24, 7 (2023)
37370	0.874	Shir B.; Prakash Verma J.; Bhattacharya P.	Mobility Prediction For Uneven Distribution Of Bikes In Bike Sharing Systems	Concurrency and Computation: Practice and Experience, 35, 2 (2023)