Probabilistic Deep Learning for Traffic Density Prediction
- 4 December 2025
- journal article
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2680 (7) , 711-730
Abstract
Real time, accurate predictions of recurrent and nonrecurrent traffic congestion are essential for optimizing transportation systems and ensuring a smooth user experience. Traditional models often focus on long-term point estimates, limiting their use in scenarios requiring short-term predictions or probabilistic assessments (e.g., traffic signal optimization, dynamic tolling, and emergency response). This study explores probabilistic deep learning (DL) for real time traffic density distribution prediction. This study demonstrates that an adapted multi-quantile recurrent neural network (MQRNN), termed MQRNN-monotonic, outperforms traditional time series methods, particularly when handling nonrecurrent disruptions. A novel loss function is introduced to address quantile crossing issues, ensuring valid distributional predictions. Experiments on two highway data sets show that probabilistic DL for traffic density prediction yields well-calibrated and sharp dynamic traffic congestion distributions. This study offers a promising new approach to real time traffic density forecasting, paving the way for transportation systems that respond faster and smarter to changing road conditions, making traffic smoother, more sustainable, and more predictable for everyone.Keywords
This publication has 80 references indexed in Scilit:
- Traffic density on corridors subject to incidents: models for long-term congestion managementEURO Journal on Transportation and Logistics, 2019
- Survey of neural network‐based models for short‐term traffic state predictionWIREs Data Mining and Knowledge Discovery, 2018
- Comparative Evaluation of Density Estimation Methods on Different Uninterrupted Roadway Facilities: Few Case Studies in IndiaTransportation in Developing Economies, 2017
- Simultaneous estimation of quantile curves using quantile sheetsAStA Advances in Statistical Analysis, 2012
- Gradient descent algorithms for quantile regression with smooth approximationInternational Journal of Machine Learning and Cybernetics, 2011
- The cell transmission model: A dynamic representation of highway traffic consistent with the hydrodynamic theoryTransportation Research Part B: Methodological, 1994
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- On tests for non‐linearity in time series analysisJournal of Forecasting, 1986
- Generalized autoregressive conditional heteroskedasticityJournal of Econometrics, 1986