01663092

Component

The station-free sharing bike is a new sharing traffic mode that has been deployed in a large scale in China in the early 2017. Without docking stations, this system allows the sharing bike to be parked in any proper places. This study aimed to develop a dynamic demand forecasting model for station-free bike sharing using the deep learning approach. The spatial and temporal analyses were first conducted to investigate the mobility pattern of the station-free bike sharing. The result indicates the imbalanced spatial and temporal demand of bike sharing trips. The long short-term memory neural networks (LSTM NN) were developed to predict the bike sharing trip production and attraction at traffic analysis zones (TAZ) for different time intervals, including the 10-min, 15-min, 20-min and 30-min intervals. The validation results suggested that the developed LSTM NN models have reasonable good prediction accuracy in trip productions and attractions for different time intervals. The ARIMA models were also developed to benchmark the LSTM NN. The comparison results suggested that the LSTM NN models provide better prediction accuracy than the ARIMA model for different time intervals. The developed LSTM NN can be used to predict the gap between sharing bike inflow and outflow, which provide useful information for rebalancing the sharing bike in the system.

This paper was sponsored by TRB committee ANF20 Standing Committee on Bicycle Transportation.

18-06476

English

6p

2018

Transportation Research Board 97th Annual Meeting

Digital/other

Figures; References; Tables

Bicycles; Forecasting; Machine learning; Neural networks; Spatial analysis; Time; Traffic analysis zones; Travel demand; Vehicle sharing

China

Pedestrians and Bicyclists; Planning and Forecasting; Vehicles and Equipment

Transportation Research Board Annual Meeting 2018 Paper #18-06476

TRIS, TRB, ATRI

Jan 8 2018 11:40AM