skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Network Scale Travel Time Prediction using Deep Learning

Abstract

In recent years, deep learning models have been receiving increased attention within the artificial intelligence (AI) community because of their high prediction accuracy. In this paper, two deep learning models, long short-term memory (LSTM) and convolutional neural network (CNN), are proposed to predict travel time in a road network. One major advantage of using deep learning for travel time prediction is that it can make accurate predictions for all the segments in the transportation network with a single model structure, instead of building customized models for each segment separately. The proposed models were evaluated on a transportation network in the City of Saint Louis, Missouri. The prediction results show that deep learning can provide accurate prediction for both congested and uncongested traffic conditions, and can successfully capture the traffic dynamics of unexpected incidents or special events. The study findings show that deep learning offers a promising approach to real-time prediction of travel times on a network scale.

Authors:
 [1];  [2]
  1. National Renewable Energy Laboratory, Golden, CO
  2. University of Missouri-Columbia, Columbia, MO
Publication Date:
Research Org.:
National Renewable Energy Lab. (NREL), Golden, CO (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE)
OSTI Identifier:
1461366
Report Number(s):
NREL/JA-5400-71974
Journal ID: ISSN 0361-1981
DOE Contract Number:  
AC36-08GO28308
Resource Type:
Journal Article
Journal Name:
Transportation Research Record
Additional Journal Information:
Journal Volume: 0; Journal Issue: 0; Journal ID: ISSN 0361-1981
Publisher:
National Academy of Sciences, Engineering and Medicine
Country of Publication:
United States
Language:
English
Subject:
33 ADVANCED PROPULSION SYSTEMS; forecasting; long short-term memory; motor transportation; time varying control systems; traffic control; travel time

Citation Formats

Hou, Yi, and Edara, Praveen. Network Scale Travel Time Prediction using Deep Learning. United States: N. p., 2018. Web. doi:10.1177/0361198118776139.
Hou, Yi, & Edara, Praveen. Network Scale Travel Time Prediction using Deep Learning. United States. doi:10.1177/0361198118776139.
Hou, Yi, and Edara, Praveen. Mon . "Network Scale Travel Time Prediction using Deep Learning". United States. doi:10.1177/0361198118776139.
@article{osti_1461366,
title = {Network Scale Travel Time Prediction using Deep Learning},
author = {Hou, Yi and Edara, Praveen},
abstractNote = {In recent years, deep learning models have been receiving increased attention within the artificial intelligence (AI) community because of their high prediction accuracy. In this paper, two deep learning models, long short-term memory (LSTM) and convolutional neural network (CNN), are proposed to predict travel time in a road network. One major advantage of using deep learning for travel time prediction is that it can make accurate predictions for all the segments in the transportation network with a single model structure, instead of building customized models for each segment separately. The proposed models were evaluated on a transportation network in the City of Saint Louis, Missouri. The prediction results show that deep learning can provide accurate prediction for both congested and uncongested traffic conditions, and can successfully capture the traffic dynamics of unexpected incidents or special events. The study findings show that deep learning offers a promising approach to real-time prediction of travel times on a network scale.},
doi = {10.1177/0361198118776139},
journal = {Transportation Research Record},
issn = {0361-1981},
number = 0,
volume = 0,
place = {United States},
year = {2018},
month = {6}
}

Works referenced in this record:

Bayesian committee of neural networks to predict travel times with confidence intervals
journal, October 2009

  • van Hinsbergen, C. P. Ij.; van Lint, J. W. C.; van Zuylen, H. J.
  • Transportation Research Part C: Emerging Technologies, Vol. 17, Issue 5
  • DOI: 10.1016/j.trc.2009.04.007

Freeway Travel-Time Estimation Based on Temporal–Spatial Queueing Model
journal, September 2013

  • Li, Li; Chen, Xiqun; Li, Zhiheng
  • IEEE Transactions on Intelligent Transportation Systems, Vol. 14, Issue 3
  • DOI: 10.1109/TITS.2013.2256132

Network-Scale Traffic Modeling and Forecasting with Graphical Lasso and Neural Networks
journal, November 2012


Travel-Time Prediction With Support Vector Regression
journal, December 2004

  • Wu, C. -H.; Ho, J. -M.; Lee, D. T.
  • IEEE Transactions on Intelligent Transportation Systems, Vol. 5, Issue 4
  • DOI: 10.1109/TITS.2004.837813

A Bayesian Network Approach to Traffic Flow Forecasting
journal, March 2006

  • Sun, S.; Zhang, C.; Yu, G.
  • IEEE Transactions on Intelligent Transportation Systems, Vol. 7, Issue 1
  • DOI: 10.1109/TITS.2006.869623

Efficient missing data imputing for traffic flow by considering temporal and spatial dependence
journal, September 2013

  • Li, Li; Li, Yuebiao; Li, Zhiheng
  • Transportation Research Part C: Emerging Technologies, Vol. 34
  • DOI: 10.1016/j.trc.2013.05.008

Traffic Prediction Using Multivariate Nonparametric Regression
journal, March 2003


Multimodel Ensemble for Freeway Traffic State Estimations
journal, June 2014

  • Li, Li; Chen, Xiqun; Zhang, Lei
  • IEEE Transactions on Intelligent Transportation Systems, Vol. 15, Issue 3
  • DOI: 10.1109/TITS.2014.2299542

A bayesian dynamic linear model approach for real-time short-term freeway travel time prediction
journal, December 2011

  • Fei, Xiang; Lu, Chung-Cheng; Liu, Ke
  • Transportation Research Part C: Emerging Technologies, Vol. 19, Issue 6
  • DOI: 10.1016/j.trc.2010.10.005

Accurate freeway travel time prediction with state-space neural networks under missing data
journal, October 2005

  • van Lint, J. W. C.; Hoogendoorn, S. P.; van Zuylen, H. J.
  • Transportation Research Part C: Emerging Technologies, Vol. 13, Issue 5-6
  • DOI: 10.1016/j.trc.2005.03.001

Traffic Flow Forecasting: Comparison of Modeling Approaches
journal, July 1997


Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory
journal, March 2015


Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks
journal, April 2012

  • Wei, Yu; Chen, Mu-Chen
  • Transportation Research Part C: Emerging Technologies, Vol. 21, Issue 1
  • DOI: 10.1016/j.trc.2011.06.009

Traffic flow forecasting by seasonal SVR with chaotic simulated annealing algorithm
journal, June 2011


Real-time road traffic prediction with spatio-temporal correlations
journal, August 2011

  • Min, Wanli; Wynter, Laura
  • Transportation Research Part C: Emerging Technologies, Vol. 19, Issue 4
  • DOI: 10.1016/j.trc.2010.10.002

Application of Subset Autoregressive Integrated Moving Average Model for Short-Term Freeway Traffic Volume Forecasting
journal, January 1999

  • Lee, Sangsoo; Fambro, Daniel B.
  • Transportation Research Record: Journal of the Transportation Research Board, Vol. 1678, Issue 1
  • DOI: 10.3141/1678-22

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data
journal, May 2015

  • Ma, Xiaolei; Tao, Zhimin; Wang, Yinhai
  • Transportation Research Part C: Emerging Technologies, Vol. 54
  • DOI: 10.1016/j.trc.2015.03.014

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction
journal, April 2017

  • Ma, Xiaolei; Dai, Zhuang; He, Zhengbing
  • Sensors, Vol. 17, Issue 4
  • DOI: 10.3390/s17040818

Long Short-Term Memory
journal, November 1997


Short-term traffic speed forecasting hybrid model based on Chaos–Wavelet Analysis-Support Vector Machine theory
journal, February 2013


Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning
journal, October 2014

  • Huang, Wenhao; Song, Guojie; Hong, Haikun
  • IEEE Transactions on Intelligent Transportation Systems, Vol. 15, Issue 5
  • DOI: 10.1109/TITS.2014.2311123

Urban Freeway Traffic Flow Prediction: Application of Seasonal Autoregressive Integrated Moving Average and Exponential Smoothing Models
journal, January 1998

  • Williams, Billy M.; Durvasula, Priya K.; Brown, Donald E.
  • Transportation Research Record: Journal of the Transportation Research Board, Vol. 1644, Issue 1
  • DOI: 10.3141/1644-14

Dynamic Freeway Travel-Time Prediction with Probe Vehicle Data: Link Based Versus Path Based
journal, January 2001

  • Chen, Mei; Chien, Steven I. J.
  • Transportation Research Record: Journal of the Transportation Research Board, Vol. 1768, Issue 1
  • DOI: 10.3141/1768-19

Online Learning Solutions for Freeway Travel Time Prediction
journal, March 2008

  • van Lint, J. W. C.
  • IEEE Transactions on Intelligent Transportation Systems, Vol. 9, Issue 1
  • DOI: 10.1109/TITS.2008.915649