Long-Term Traffic Prediction Using Deep Learning Long Short-Term Memory
Ange-Lionel Toba, Sameer Kulkarni, Wael Khallouli, Timothy Pennington
Abstract
Traffic conditions are a key factor in our society, contributing to quality of life and the economy, as well as access to professional, educational, and health resources. This emphasizes the need for a reliable road network to facilitate traffic fluidity across the nation and improve mobility. Reaching these characteristics demands good traffic volume prediction methods, not only in the short term but also in the long term, which helps design transportation strategies and road planning. However, most of the research has focused on short-term prediction, applied mostly to short-trip distances, while effective long-term forecasting, which has become a challenging issue in recent years, is lacking. The team proposes a traffic prediction method that leverages K-means clustering, long short-term memory (LSTM) neural network, and Fourier transform (FT) for long-term traffic prediction. The proposed method was evaluated on a real-world dataset from the U.S. Travel Monitoring Analysis System (TMAS) database, which enhances practical relevance and potential impact on transportation planning and management. The forecasting performance is evaluated with real-world traffic flow data in the state of California, in the western USA. Results show good forecasting accuracy on traffic trends and counts over a one-year period, capturing periodicity and variation.