Short Term Prediction of Urban Traffic Flow based on Machine Learning Algorithms

With the increasing per capita car ownership worldwide, existing transportation facilities are unable to fully meet people's travel needs. The massive traffic flow can lead to traffic congestion, so predicting traffic flow can play a crucial role in urban traffic management. This study predicts the westbound traffic flow data of the Minnesota Department of Transportation (MN DoT) ATR 301 station on Interstate 94 in the United States for 28 consecutive days using a Long Short-Term Memory Network (LSTM) data prediction model. The Random Forest is utilized to analyze the association between attributes and the historical data has been separated into 1-hour intervals. The highway displays a bimodal pattern on weekdays and a unimodal pattern on holidays, according to the final forecast results. Furthermore, after making the necessary adjustments to the parameters, the simulated trend closely resembles the real value, proving that LSTM can be used to model short-term traffic flow. Accurately predicting urban traffic flow can make the management of urban traffic management systems more comprehensive and provide citizens with higher quality travel planning references.