Research on Forecasting Short-term Passenger Flow of Subway Based on Deep Neural Network

Abstract

With the rapid development of urbanization, a large number of people have poured into cities, which makes the traffic congestion problem increasingly serious. As a stable, efficient, safe and environmentally friendly public transport, subway has gradually become the first choice for residents to travel by bus. The rapid increase in the number of passengers has caused great pressure on the quality of subway operation and service. Therefore, how to accurately predict the passenger flow of the station at a certain time in the future and let the subway operation department make the corresponding operation plan in advance according to the predicted passenger flow is of great significance to improve the service quality of subway operation. Under this background, this paper summarizes the existing short-term passenger flow forecasting methods at home and abroad, and puts forward the application of deep neural network method in the field of short-term passenger flow forecasting of urban rail transit according to the advantages and disadvantages of different forecasting methods. Taking the short-term passenger flow forecast of Nanjing subway as an example, the original credit card data is preprocessed to obtain passenger flow data, and the temporal and spatial distribution law of historical passenger flow is studied, and the LSTM prediction model and CNN-LSTM combined prediction model are established, which improves the prediction accuracy of short-term inbound passenger flow of rail transit.