Combining weather condition data to predict traffic flow: a GRU‐based deep learning approach

TLDR

Traffic flow prediction is an essential component of the intelligent transportation management system. The study applies a gated recurrent neural network to predict urban traffic flow while incorporating weather conditions. The authors use a gated recurrent unit–based deep learning framework that integrates extensive weather data to model traffic flow. Results demonstrate that incorporating weather data improves predictive accuracy and reduces error rates, marking the first use of this approach for urban freeway traffic flow.

Abstract

Traffic flow prediction is an essential component of the intelligent transportation management system. This study applies gated recurrent neural network to predict urban traffic flow considering weather conditions. Running results show that, under the review of weather influences, their method improves predictive accuracy and also decreases the prediction error rate. To their best knowledge, this is the first time that traffic flow is predicted in urban freeways in this particular way. This study examines it with respect to extensive weather influence under gated recurrent unit‐based deep learning framework.