A Spatiotemporal Prediction Model for Regional Scheduling of Shared Bicycles Based on the INLA Method

Zhuoran Yu,Yimeng Duan,Xin Liu,Shen Zhang,Kui Li,Xinqiang Chen

doi:10.1155/2021/4959504

Abstract

Dock-less bicycle-sharing programs have been widely accepted as an efficient mode to benefit health and reduce congestions. And modeling and prediction has always been a core proposition in the field of transportation. Most of the existing demand prediction models for shared bikes take regions as research objects; therefore, a POI-based method can be a beneficial complement to existing research, including zone-level, OD-level, and station-level techniques. Point of interest (POI) is the location description of spatial entities, which can reflect the cycling route characteristics for both commuting and noncommuting trips to a certain extent, and is also the main generating point and attraction point of shared-bike travel flow. In this study, we make an effort to model a POI-level cycling demand with a Bayesian hierarchical method. The proposed model combines the integrated nested Laplace approximation (INLA) and random partial differential equation (SPDE) to cope with the huge computation in the modeling process. In particular, we have adopted the dock-less bicycle-sharing rental records of Mobike as a case study to validate our method; the study area was one of the fastest growing urban districts in Shanghai in August 2016. The operation results show that the method can help better understand, measure, and characterize spatiotemporal patterns of bike-share ridership at the POI level and quantify the impact of the spatiotemporal effect on bicycle-sharing use.

Highlights

Bike-sharing is a service that allows the public to rent bicycles on a time-sharing basis, relying on the Internet to make full use of the demand for self-transportation brought about by rapid urban development [1]
In order to achieve this goal, a Bayesian hierarchical spatiotemporal model was established based on the multiple source data such as Point of interest (POI), daily weather, and dock-less bike-sharing data
E use of the integrated nested Laplace approximation (INLA) method and stochastic partial differential equation (SPDE) approach in our model greatly reduced the computation time compared with the traditional Markov Chain Monte Carlo (MCMC) method

Summary

Introduction

Bike-sharing is a service that allows the public to rent bicycles on a time-sharing basis, relying on the Internet to make full use of the demand for self-transportation brought about by rapid urban development [1]. Erefore, a POI-based study on bike-sharing travel can combine the use characteristics of bike-sharing with the travel needs and help understand the circulation characteristics and service capacity of urban hot areas, filling the blank of existing studies Another thing worth notice is the method of prediction. Many research efforts have been made to predict bike-share demand based on various machine learning models, such as clustering analysis [9], k-nearest neighbors [10], support vector machine (SVM) [11], and artificial neural network (ANN) [12] These models are lack of well consideration for some factors, such as requiring a large amount of observation data, only taking regions as objects for research, and failing to take into account the change in the space-time dimension of the number of shared-bike trips. The combination of INLA algorithm and SPDE method has been widely used in various fields, such as the evolution of Ebola virus and climate impact [19], but rarely applied in the field of traffic characteristic analyzing. e framework of this paper is as follows: the second part shows the methods used, the third part carries out the model architecture and calculation, and the fourth part discusses the research results

Model Methods

Analysis and Discussion

Conclusion