Traffic incidents significantly disrupt freeway operations, causing delays, congestion, fuel waste, and economic losses. Effective incident management requires not only rapid detection and clearance but also accurate real-time prediction of incident duration, a capability currently lacking in most Traffic Management Centers (TMCs). This study develops machine learning models to predict incident duration based on real-time responses and evolving incident conditions. The analysis uses incident data from the I-15 corridor in Las Vegas, Nevada, encompassing 643 recorded incidents, of which 272 were further documented in a novel Video Snapshots Dataset (VSDS) that captures 15-second visual records of incident characteristics. Key incident attributes, including total and average blockage duration, were extracted to enrich model training. Three predictive approaches were evaluated: Lasso Regression and Ridge Regression with 10-fold cross-validation, with comparison with Multiple Linear Regression. Among these, Ridge Regression achieved the highest predictive accuracy, demonstrating its effectiveness for real-time estimation of incident duration. These findings provide a foundation for enhancing TMC operations by enabling more reliable travel time updates and proactive traffic management strategies.
References
[1]
NHTSA (2017) Summary of Motor Vehicle Crashes (Final Edition): 2015 Data. Report No. DOT HS 812 376, National Highway Traffic Safety Administration, U.S. Department of Transportation.
[2]
NHTSA (2023) Summary of Motor Vehicle Crashes: 2021 Data. Report No. DOT HS 813 515, National Highway Traffic Safety Administration, U.S. Department of Transportation.
[3]
Garib, A., Radwan, A.E. and Al-Deek, H. (1997) Estimating Magnitude and Duration of Incident Delays. JournalofTransportationEngineering, 123, 459-466. https://doi.org/10.1061/(asce)0733-947x(1997)123:6(459)
[4]
Valenti, G., Lelli, M. and Cucina, D. (2010) A Comparative Study of Models for the Incident Duration Prediction. EuropeanTransportResearchReview, 2, 103-111. https://doi.org/10.1007/s12544-010-0031-4
[5]
Khattak, A., Wang, X. and Zhang, H. (2012) Incident Management Integration Tool: Dynamically Predicting Incident Durations, Secondary Incident Occurrence and Incident Delays. IETIntelligentTransportSystems, 6, 204-214. https://doi.org/10.1049/iet-its.2011.0013
[6]
Pereira, F.C., Rodrigues, F. and Ben-Akiva, M. (2013) Text Analysis in Incident Duration Prediction. TransportationResearchPartC: EmergingTechnologies, 37, 177-192. https://doi.org/10.1016/j.trc.2013.10.002
[7]
Corbally, R., Yang, L. and Malekjafarian, A. (2024) Predicting the Duration of Motorway Incidents Using Machine Learning. EuropeanTransportResearchReview, 16, Article No. 14. https://doi.org/10.1186/s12544-024-00632-6
[8]
Yu, B. and Xia, Z. (2012) A Methodology for Freeway Incident Duration Prediction Using Computerized Historical Database. In: Fang, F.C., Wei, H. and Wang, Y.P., Eds., CICTP 2012: Multimodal Transportation Systems—Convenient, Safe, Cost-Effective, Efficient, American Society of Civil Engineers, 3463-3474. https://doi.org/10.1061/9780784412442.351
[9]
Khattak, A.J., Schofer, J.L. and Wang, M. (1995) A Simple Time Sequential Procedure for Predicting Freeway Incident Duration. IVHSJournal, 2, 113-138. https://doi.org/10.1080/10248079508903820
[10]
Lee, J.Y., Chung, J.H. AND Son, B. (2009) Incident Clearance Time Analysis for Korean Freeways Using Structural Equation Model. Proceedings of the Eastern Asia Society for Transportation Studies, 7. https://doi.org/10.11175/eastpro.2009.0.360.0
[11]
Khattak, A.J., Liu, J., Wali, B., Li, X. and Ng, M. (2016) Modeling Traffic Incident Duration Using Quantile Regression. TransportationResearchRecord: JournaloftheTransportationResearchBoard, 2554, 139-148. https://doi.org/10.3141/2554-15
[12]
Ding, C., Ma, X., Wang, Y. and Wang, Y. (2015) Exploring the Influential Factors in Incident Clearance Time: Disentangling Causation from Self-Selection Bias. AccidentAnalysis&Prevention, 85, 58-65. https://doi.org/10.1016/j.aap.2015.08.024
[13]
Qi, Y. and Teng, H. (2008) An Information-Based Time Sequential Approach to Online Incident Duration Prediction. JournalofIntelligentTransportationSystems, 12, 1-12. https://doi.org/10.1080/15472450701849626
[14]
Kalair, K. and Connaughton, C. (2021) Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations. FrontiersinFutureTransportation, 2, Article 669015. https://doi.org/10.3389/ffutr.2021.669015
[15]
Mohammed, Z.A., Abdullah, M.N. and Al Hussaini, I.H. (2021) Predicting Incident Duration Based on Machine Learning Methods. Iraqi Journal of Computers, Communications, Control and Systems Engineering, 21, 1-15.
[16]
Kuang, L., Yan, H., Zhu, Y., Tu, S. and Fan, X. (2019) Predicting Duration of Traffic Accidents Based on Cost-Sensitive Bayesian Network and Weighted K-Nearest Neighbor. JournalofIntelligentTransportationSystems, 23, 161-174. https://doi.org/10.1080/15472450.2018.1536978
[17]
Zou, Y., Lin, B., Yang, X., Wu, L., Muneeb Abid, M. and Tang, J. (2021) Application of the Bayesian Model Averaging in Analyzing Freeway Traffic Incident Clearance Time for Emergency Management. JournalofAdvancedTransportation, 2021, Article ID: 6671983. https://doi.org/10.1155/2021/6671983
[18]
Dimitriou, L. and Vlahogianni, E.I. (2015) Fuzzy Modeling of Freeway Accident Duration with Rainfall and Traffic Flow Interactions. AnalyticMethodsinAccidentResearch, 5, 59-71. https://doi.org/10.1016/j.amar.2015.04.001
[19]
Hamad, K., Khalil, M.A. and Alozi, A.R. (2019) Predicting Freeway Incident Duration Using Machine Learning. InternationalJournalofIntelligentTransportationSystemsResearch, 18, 367-380. https://doi.org/10.1007/s13177-019-00205-1
[20]
Shan, L., Yang, Z., Zhang, H., Shi, R. and Kuang, L. (2019) Predicting Duration of Traffic Accidents Based on Ensemble Learning. In: Gao, H., Wang, X., Yin, Y. and Iqbal, M., Eds., Collaborative Computing: Networking, Applications and Worksharing, Springer, 252-266. https://doi.org/10.1007/978-3-030-12981-1_18
[21]
Hamad, K., Al-Ruzouq, R., Zeiada, W., Abu Dabous, S. and Khalil, M.A. (2020) Predicting Incident Duration Using Random Forests. TransportmetricaA: TransportScience, 16, 1269-1293. https://doi.org/10.1080/23249935.2020.1733132
[22]
Weng, J., Qiao, W., Qu, X. and Yan, X. (2015) Cluster-Based Lognormal Distribution Model for Accident Duration. TransportmetricaA: TransportScience, 11, 345-363. https://doi.org/10.1080/23249935.2014.994687
[23]
Zhao, H., Gunardi, W., Liu, Y., Kiew, C., Teng, T. and Yang, X.B. (2022) Prediction of Traffic Incident Duration Using Clustering-Based Ensemble Learning Method. JournalofTransportationEngineering, PartA: Systems, 148, Article ID: 04022044. https://doi.org/10.1061/jtepbs.0000688
