Attention-LSTM Based Modelling for Hangzhou City Metro Passenger Flow Forecasting Study

With the expanding scale of urbanisation, urban traffic problems are increasing, and traffic flow prediction is often of great significance as the core of intelligent transport system (ITS) to solve traffic problems. This paper firstly analyses the temporal and spatial characteristics of the urban traffic flow prediction problem, and for the temporal and spatial characteristics, respectively, establishes a long and short-term memory network LSTM urban traffic flow prediction model based on the attention mechanism; finally, based on the kaggle dataset, the Hangzhou metro passenger flow dataset is used for the effect test of the model, and the results show that the model has a good predictive effect for the prediction of the Hangzhou metro passenger flow. The results show that the model has good prediction effect for passenger flow prediction in Hangzhou metro.