Short-term passenger flow prediction of rail transit based on VMD-LSTM neural network combination model

Abstract

The short-term passenger flow of urban rail transit has obvious characteristics of non-linearity and non-stationarity, and the traditional prediction method has poor accuracy. Based on this, this paper proposes a VMD-LSTM combination model for the prediction of short-term passenger flow in urban rail transit and verifies it by an example. The results show that: (1) the prediction effect of the LSTM neural network is better than the RNN neural network; (2) the VMD-LSTM neural network combined model prediction is more accurate than the prediction using the LSTM neural network alone. Therefore, the combined model is suitable for the prediction of short-term passenger flow in rail transit, which helps the subway company to grasp the law of passenger flow change, so as to formulate a practical traffic management plan and improve operational efficiency.