Traffic flow forecasting is a task that is becoming increasingly important in this modern world. People use various navigation systems, including a prediction model that provides the estimated time for reaching a destination and its optimal path. The core of those systems is the traffic flow forecasting model. Although there are many forecasting models currently in use, their performance has proven to be insufficient in many situations. In this experiment, we used Temporal Fusion Transformers (TFT) to predict the average occupancy of real-life traffic from some roadside units in California. Extensive hyperparameter tuning is performed to ensure optimal results for the model. TFT outperformed all the state-of-the-art models with a precision of around 95%. Our implementation of quantile probabilistic forecasting on the data adds another layer of forecasting information and has demonstrated that the actual values mostly lie within the confidence interval range, which makes the model more useful for making navigation decisions in a traffic forecasting system.
Time-series Multivariate Multistep Traffic Flow Forecasting using Temporal Fusion Transformers
Int. J. ITS Res.
International Journal of Intelligent Transportation Systems Research ; 23 , 1 ; 622-628
2025-04-01
7 pages
Article (Journal)
Electronic Resource
English
Intelligent transportation system , PeMS , Confidence interval , Average occupancy Engineering , Electrical Engineering , Automotive Engineering , Robotics and Automation , Computer Imaging, Vision, Pattern Recognition and Graphics , Civil Engineering , User Interfaces and Human Computer Interaction
Time-series Multivariate Multistep Traffic Flow Forecasting using Temporal Fusion Transformers
Springer Verlag | 2025
|Multivariate Short-Term Traffic Flow Forecasting Using Time-Series Analysis
Online Contents | 2009
|Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction
DOAJ | 2020
|