Abstract
Bike-sharing systems have made notable contributions to cities by providing green and sustainable mobility service to users. Over the years, many studies have been conducted to understand or anticipate the usage of these systems, with the hope to inform their future developments. One important task is to accurately predict usage patterns of the systems. Although many deep learning algorithms have been developed in recent years to support travel demand forecast, they have mainly been used to predict traffic volume or speed on roadways. Few studies have applied them to bike-sharing systems. Moreover, these studies usually focus on one single dataset or study area. The effectiveness and robustness of the prediction algorithms are not systematically evaluated. In this study, we propose a Spatial-Temporal Memory Network (STMN) to predict short-term usage of bicycles in bike-sharing systems. The framework employs Convolutional Long Short-Term Memory models and a feature engineering technique to capture the spatial-temporal dependencies in historical data for the prediction task. Four testing sites are used to evaluate the model. These four sites include two station-based systems (Chicago and New York) and two dockless bike-sharing systems (Singapore and New Taipei City). By assessing STMN with several baseline models, we find that STMN achieves the best overall performance in all the four cities. The model also achieves superior performance in urban areas with varying levels of bicycle usage and during peak periods when demand is high. The findings suggest the reliability of STMN in predicting bicycle usage for different types of bike-sharing systems.
Highlights
I N THE past few decades, with increasing concerns over global warming and energy consumption, cities around the world have made notable efforts to promote bike-sharing systems as a green mobility strategy
The value of each cell represents the number of travels that start from this cell during one hour, excluding travels ending in the same cell
We find that Spatial-Temporal Memory Network (STMN)-WCAT outperforms other deep learning models at all four quantiles of bicycle usage on most datasets
Summary
I N THE past few decades, with increasing concerns over global warming and energy consumption, cities around the world have made notable efforts to promote bike-sharing systems as a green mobility strategy. Some hybrid deep learning frameworks are developed to integrate convolution and RNN based methods to better capture the spatial-temporal dependency [23], [24]. There are a limited number of studies using such hybrid frameworks for predicting bicycle usage in bike-sharing systems. The performance of these hybrid frameworks is usually assessed over one single dataset or study area [14], [16] The effectiveness of these models has not been systematically evaluated across different types of bike-sharing systems. We propose a Spatial-Temporal Memory Network (STMN) to predict bicycle usage in both station-based and free-floating bike-sharing systems. The framework incorporates Convolutional Long Short-Term Memory module (Conv-LSTM) [30] to capture spatial-temporal dependency in bicycle usage across urban locations. We discuss the implications of the study and propose future works
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Intelligent Transportation Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
