Shared Cycling Demand Prediction during COVID-19 Combined with Urban Computing and Spatiotemporal Residual Network

Abstract

The regularity and demand predictions of shared cycling are very necessary and challenging for the management and development of urban pedestrian and bicycle traffic. The bicycle-sharing system has the problem of spatial and temporal demand fluctuations and presents a very complex nonlinear regularity. The demand for shared bicycles is affected by many factors, including time, space, weather and the situation of COVID-19. This study proposes a new bicycle-sharing demand forecasting model (USTARN) based on the impact of COVID-19, which combines urban computing and spatiotemporal attention residual network. USTARN consists of two parts. In the first part, a spatiotemporal attention residual network model is established to learn the temporal correlation and spatial correlation of shared bicycle demand. The temporal characteristic branches of each spatial small region are trained, respectively, to predict the shared bicycle demand in batches in different regions and periods according to the historical data. In order to improve the prediction accuracy of the model, the second part of the model adjusts and redistributes the prediction results of the first part by learning other information of the city, such as the severity of COVID-19, weather, temperature, wind speed and holidays. It can predict the demand for shared bicycles in different urban areas in different periods and different severities of COVID-19. This study uses the order data of shared bicycles during the period of COVID-19 in 2020 obtained from the open data platform of Shenzhen municipal government as verification, analyzes the spatiotemporal regularity of the system demand and discusses the impact of the number of newly diagnosed patients and the daily minimum temperature on the demand for shared bicycles. The results show that USTARN can fully reflect time, space, the epidemic situation, weather and temperature, and the prediction results of the impact of wind speed and other factors on the demand for shared bicycles are better than the classical methods.