Traffic congestion caused by nonrecurring incidents such as vehicle crashes and debris is a key issue for Traffic Management Centers (TMCs). Clearing incidents in a timely manner is essential to improve safety and reduce delays and emissions for the traveling public. However, TMCs and other responders face a challenge in predicting the duration of incidents (until the roadway is clear), making decisions about what resources to deploy is difficult. To address this problem, this research developed an analytical framework and end-to-end machine learning solution to predict the duration of the incident based on the information available as soon as an incident report is received. Quality predictions of incident duration can help TMCs and other responders take a proactive approach in deploying responder services such as tow trucks, and maintenance crews, or activating alternative routes. The predictions use a combination of classification and regression machine learning modules. The performance of the developed solution has been evaluated based on the Mean Absolute Error (MAE), or deviation from the actual incident duration as well as Area Under the Curve (AUC) and Mean Absolute Percentage Error (MAPE). The results showed that the framework significantly improved the prediction of incident duration compared to previous research methods.
References
[1]
Farradyne, P. (2000) Traffic Incident Management Handbook. Federal High-Way Administration, Office of Travel Management. https://transops.s3.amazonaws.com/uploaded_files/FHWA-HOP-10-013-Traffic-Incident-Management-Handbook.pdf
[2]
Park, H., Haghani, A., Samuel, S. and Knodler, M.A. (2018) Real-Time Prediction and Avoidance of Secondary Crashes under Unexpected Traffic Congestion. Accident Analysis & Prevention, 112, 39-49. https://doi.org/10.1016/j.aap.2017.11.025
[3]
Cong, H., Chen, C., Lin, P., Zhang, G., Milton, J. and Zhi, Y. (2018) Traffic Incident Duration Estimation Based on a Dual-Learning Bayesian Network Model. Transportation Research Record: Journal of the Transportation Research Board, 2672, 196-209. https://doi.org/10.1177/0361198118796938
[4]
Oh, M., Wood, J. and Dong-O’Brien, J. (2023) The Integrated Analysis of Primary and Secondary Incident Characteristics: Focusing on the Impact and Scope of the Safety Service Patrol Program in Iowa. Heliyon, 9, e17759. https://doi.org/10.1016/j.heliyon.2023.e17759
[5]
Garib, A., Radwan, A.E. and Al-Deek, H. (1997) Estimating Magnitude and Duration of Incident Delays. Journal of Transportation Engineering, 123, 459-466. https://doi.org/10.1061/(asce)0733-947x(1997)123:6(459)
[6]
Peeta, S., Ramos, J.L. and Gedela, S. (2000) Providing Real-Time Traffic Advisory and Route Guidance to Manage Borman Incidents Online Using the Hoosier Helper Program. https://doi.org/10.5703/1288284313298
[7]
Yu, B. and Xia, Z. (2012) A Methodology for Freeway Incident Duration Prediction Using Computerized Historical Database. CICTP 2012, Beijing, 3-6 August 2012, 3463-3474. https://doi.org/10.1061/9780784412442.351
[8]
Weng, J., Qiao, W., Qu, X. and Yan, X. (2015) Cluster-Based Lognormal Distribution Model for Accident Duration. Transportmetrica A: Transport Science, 11, 345-363. https://doi.org/10.1080/23249935.2014.994687
[9]
Dimitriou, L. and Vlahogianni, E.I. (2015) Fuzzy Modeling of Freeway Accident Duration with Rainfall and Traffic Flow Interactions. Analytic Methods in Accident Research, 5, 59-71. https://doi.org/10.1016/j.amar.2015.04.001
[10]
Kim, H.J. and Choi, H. (2001) A Comparative Analysis of Incident Service Time on Urban Freeways. IATSS Research, 25, 62-72. https://doi.org/10.1016/s0386-1112(14)60007-8
[11]
Pereira, F.C., Rodrigues, F. and Ben-Akiva, M. (2013) Text Analysis in Incident Duration Prediction. Transportation Research Part C: Emerging Technologies, 37, 177-192. https://doi.org/10.1016/j.trc.2013.10.002
[12]
Lopes, J., Bento, J., Pereira, F.C. and Ben-Akiva, M. (2013) Dynamic Forecast of Incident Clearance Time Using Adaptive Artificial Neural Network Models. https://trid.trb.org/View/1242255
[13]
Park, H., Haghani, A. and Zhang, X. (2015) Interpretation of Bayesian Neural Networks for Predicting the Duration of Detected Incidents. Journal of Intelligent Transportation Systems, 20, 385-400. https://doi.org/10.1080/15472450.2015.1082428
[14]
Ghosh, B., Asif, M.T. and Dauwels, J. (2016) Bayesian Prediction of the Duration of Non-Recurring Road Incidents. 2016 IEEE Region 10 Conference (TENCON), Singapore, 22-25 November 2016, 87-90. https://doi.org/10.1109/tencon.2016.7847964
[15]
Li, R. (2015) Traffic Incident Duration Analysis and Prediction Models Based on the Survival Analysis Approach. IET Intelligent Transport Systems, 9, 351-358. https://doi.org/10.1049/iet-its.2014.0036
[16]
Yang, D., Ozbay, K., Xie, K. and Yang, H. (2023) A Survival Analysis with Random Parameter Approach for Assessing Temporal Instability in Treatment Effect. Safety Science, 164, Article ID: 106182. https://doi.org/10.1016/j.ssci.2023.106182
[17]
Islam, N., Adanu, E.K., Hainen, A.M., Burdette, S., Smith, R. and Jones, S. (2021) A Comparative Analysis of Freeway Crash Incident Clearance Time Using Random Parameter and Latent Class Hazard-Based Duration Model. Accident Analysis & Prevention, 160, Article ID: 106303. https://doi.org/10.1016/j.aap.2021.106303
[18]
Chung, Y. (2010) Development of an Accident Duration Prediction Model on the Korean Freeway Systems. Accident Analysis & Prevention, 42, 282-289. https://doi.org/10.1016/j.aap.2009.08.005
[19]
Hu, J., Krishnan, R. and Bell, M. (2011) Incident Duration Prediction for In-Vehicle Navigation Systems. Transportation Research Board 90th Annual Meeting, Washington DC, 23-27 January 2011, 1-19.
[20]
Kang, G. and Fang, S. (2011) Applying Survival Analysis Approach to Traffic Incident Duration Prediction. ICTIS 2011, Wuhan, 30 June-2 July 2011, 1523-1531. https://doi.org/10.1061/41177(415)193
[21]
Thapa, D., Mishra, S., Velaga, N.R. and Patil, G.R. (2024) Advancing Proactive Crash Prediction: A Discretized Duration Approach for Predicting Crashes and Severity. Accident Analysis & Prevention, 195, Article ID: 107407. https://doi.org/10.1016/j.aap.2023.107407
[22]
Li, X., Liu, J., Khattak, A. and Nambisan, S. (2020) Sequential Prediction for Large-Scale Traffic Incident Duration: Application and Comparison of Survival Models. Transportation Research Record: Journal of the Transportation Research Board, 2674, 79-93. https://doi.org/10.1177/0361198119899041
[23]
Lin, L., Wang, Q. and Sadek, A.W. (2016) A Combined M5P Tree and Hazard-Based Duration Model for Predicting Urban Freeway Traffic Accident Durations. Accident Analysis & Prevention, 91, 114-126. https://doi.org/10.1016/j.aap.2016.03.001
[24]
Lin, P.W., Zou, N. and Chang, G.L. (2004) Integration of a Discrete Choice Model and a Rule-Based System for Estimation of Incident Duration: A Case Study in Mayland. CD-ROM of Proceedings of the 83rd TRB Annual Meeting, Washington DC, 11-15 January 2004, 1-25.
[25]
Li, R., Pereira, F.C. and Ben-Akiva, M.E. (2015) Competing Risks Mixture Model for Traffic Incident Duration Prediction. Accident Analysis & Prevention, 75, 192-201. https://doi.org/10.1016/j.aap.2014.11.023
[26]
Zhan, C., Gan, A. and Hadi, M. (2011) Prediction of Lane Clearance Time of Freeway Incidents Using the M5P Tree Algorithm. IEEE Transactions on Intelligent Transportation Systems, 12, 1549-1557. https://doi.org/10.1109/tits.2011.2161634
[27]
Knibbe, W.J.J., Alkim, T.P., Otten, J.F.W. and Aidoo, M.Y. (2006) Automated Estimation of Incident Duration on Dutch Highways. 2006 IEEE Intelligent Transportation Systems Conference, Toronto, 17-20 September 2006, 870-874. https://doi.org/10.1109/itsc.2006.1706853
[28]
He, Q., Kamarianakis, Y., Jintanakul, K. and Wynter, L. (2013) Incident Duration Prediction with Hybrid Tree-Based Quantile Regression. In: Ukkusuri, S. and Ozbay, K., Eds., Advances in Dynamic Network Modeling in Complex Transportation Systems, Springer, 287-305. https://doi.org/10.1007/978-1-4614-6243-9_12
[29]
Tang, J., Zheng, L., Han, C., Liu, F. and Cai, J. (2020) Traffic Incident Clearance Time Prediction and Influencing Factor Analysis Using Extreme Gradient Boosting Model. Journal of Advanced Transportation, 2020, Article ID: 6401082. https://doi.org/10.1155/2020/6401082
[30]
Hamad, K., Al-Ruzouq, R., Zeiada, W., Abu Dabous, S. and Khalil, M.A. (2020) Predicting Incident Duration Using Random Forests. Transportmetrica A: Transport Science, 16, 1269-1293. https://doi.org/10.1080/23249935.2020.1733132
[31]
Ghosh, B., Asif, M.T., Dauwels, J., Fastenrath, U. and Guo, H. (2019) Dynamic Prediction of the Incident Duration Using Adaptive Feature Set. IEEE Transactions on Intelligent Transportation Systems, 20, 4019-4031. https://doi.org/10.1109/tits.2018.2878637
[32]
Won, M., Kim, H. and Chang, G. (2018) Knowledge-Based System for Estimating Incident Clearance Duration for Maryland I-95. Transportation Research Record: Journal of the Transportation Research Board, 2672, 61-72. https://doi.org/10.1177/0361198118792119
[33]
Chen, J. and Tao, W. (2022) Traffic Accident Duration Prediction Using Text Mining and Ensemble Learning on Expressways. Scientific Reports, 12, Article No. 21478. https://doi.org/10.1038/s41598-022-25988-4
[34]
Chen, J., Tao, W., Jing, Z., Wang, P. and Jin, Y. (2024) Traffic Accident Duration Prediction Using Multi-Mode Data and Ensemble Deep Learning. Heliyon, 10, e25957. https://doi.org/10.1016/j.heliyon.2024.e25957
[35]
Fu, K., Ji, T., Zhao, L. and Lu, C. (2019) TITAN: A Spatiotemporal Feature Learning Framework for Traffic Incident Duration Prediction. Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Chicago, 5-8 November 2019, 329-338. https://doi.org/10.1145/3347146.3359381
[36]
Laman, H., Yasmin, S. and Eluru, N. (2018) Joint Modeling of Traffic Incident Duration Components (Reporting, Response, and Clearance Time): A Copula-Based Approach. Transportation Research Record: Journal of the Transportation Research Board, 2672, 76-89. https://doi.org/10.1177/0361198118801355
[37]
Mihaita, A.S., Liu, Z., Cai, C. and Rizoiu, M.A. (2019) Arterial Incident Duration Prediction Using a Bi-Level Framework of Extreme Gradient-Tree Boosting. arXiv: 1905.12254.
[38]
Dong, X., Yu, Z., Cao, W., Shi, Y. and Ma, Q. (2019) A Survey on Ensemble Learning. Frontiers of Computer Science, 14, 241-258. https://doi.org/10.1007/s11704-019-8208-z
[39]
Sagi, O. and Rokach, L. (2018) Ensemble Learning: A Survey. WIREs Data Mining and Knowledge Discovery, 8, e1249. https://doi.org/10.1002/widm.1249
[40]
Wang, Z., Jiao, P., Wang, J., Luo, W. and Lu, H. (2023) Improved Two-Layer Stacking Model for Prediction of the Level of Delay Caused by Crashes: An Empirical Analysis of Texas. Journal of Transportation Engineering, Part A: Systems, 149, Article ID: 05022008. https://doi.org/10.1061/jtepbs.teeng-7577
[41]
Knickerbocker, S., Jagarlamudi, V.K., Hawkins, N. and Sharma, A. (2018) Iowa Dot Traffic Operations Open Data Service: User Guide and Software Requirements Specification. https://www.iowasudas.org/wp-content/uploads/2018/07/Iowa_DOT_traffic_ops_open_data_svc_guide_w_cvr.pdf
[42]
Park, H. and Haghani, A. (2016) Real-time Prediction of Secondary Incident Occurrences Using Vehicle Probe Data. Transportation Research Part C: Emerging Technologies, 70, 69-85. https://doi.org/10.1016/j.trc.2015.03.018
[43]
Mumtarin, M., Knickerbocker, S., Litteral, T. and Wood, J.S. (2023) Traffic Incident Management Performance Measures: Ranking Agencies on Roadway Clearance Time. Journal of Transportation Technologies, 13, 353-368. https://doi.org/10.4236/jtts.2023.133017
[44]
Khattak, A., Wang, X. and Zhang, H. (2012) Incident Management Integration Tool: Dynamically Predicting Incident Durations, Secondary Incident Occurrence and Incident Delays. IET Intelligent Transport Systems, 6, 204-214. https://doi.org/10.1049/iet-its.2011.0013
[45]
Valenti, G., Lelli, M. and Cucina, D. (2010) A Comparative Study of Models for the Incident Duration Prediction. European Transport Research Review, 2, 103-111. https://doi.org/10.1007/s12544-010-0031-4
[46]
Ma, X., Ding, C., Luan, S., Wang, Y. and Wang, Y. (2017) Prioritizing Influential Factors for Freeway Incident Clearance Time Prediction Using the Gradient Boosting Decision Trees Method. IEEE Transactions on Intelligent Transportation Systems, 18, 2303-2310. https://doi.org/10.1109/tits.2016.2635719
