Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network

Abstract

Online car-hailing has brought convenience to daily travel, whose accurate prediction benefits drivers and helps managers to grasp the characteristics of urban travel, so as to facilitate decisions. Spatiotemporal prediction in the transportation field has usually been based on a recurrent neural network (RNN), which has problems such as lengthy computation and backpropagation. This paper describes a model based on a Transformer, which has shown success in computer vision. The study area is divided into grids, and the structure of travel data is converted into video frames by time period, based on predicted spatiotemporal travel demand. The predictions of the model are closest to the real data in terms of spatial distribution and travel demand when the data are divided into 10 min intervals, and the travel demand in the first two hours is used to predict demand in the next hour. We experimentally compare the proposed model with the three most commonly used spatiotemporal prediction models, and the results show that our model has the best accuracy and training speed.