Temperature Prediction for Expressway Pavement Icing in Winter Based on XGBoost–LSTNet Variable Weight Combination Model
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 149, Issue 7
Abstract
Ice cover on pavement may reduce the road adhesion coefficient and increase the crash risks, which might result in more traffic crashes. The primary factor utilized to assess whether the wet pavement is icy or not is the pavement temperature. Therefore, forecasting pavement temperature is an effective method to judge road conditions and improve traffic safety. This paper proposes a combination model based on the extreme gradient boosting (XGBoost) model and long- and short-term time-series network (LSTNet) model to predict pavement temperature. Pavement temperature and meteorological data were collected for the cities along the Shandong part of the Beijing-Taipei Expressway (G3). In this study, nine meteorological variables were used. Subsequently, after correlation analysis, five variables, including air temperature, dew point temperature, relative humidity, evaporation, and potential evaporation, were selected for prediction. The method proposed in this study comprises the following steps. First, the XGBoost and the LSTNet models are respectively formulated based on the time-varying characteristics of pavement temperatures. Then, using the preset weight of the variable, the XGBoost model is used for preliminary prediction to add features. Finally, the experimental analysis is performed on the Qihe data set after the two models have been integrated using the inverse variance method. As revealed by the experimental results, the mean absolute error (MAE) and root-mean-square error (RMSE) of the proposed XGBoost-LSTNet model are 0.8235 and 1.2412, respectively. Compared with the long short-term memory (LSTM) model, random forest (RF) model, XGBoost model, and LSTNet model, the XGBoost-LSTNet model proposed in this paper has higher accuracy. The study’s findings can successfully increase wintertime expressway traffic safety and serve as a guide for managing maintenance and preventing icing-related accidents.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This study was sponsored by Open Project of Shandong Key Laboratory of Highway Technology and Safety Assessment (SH202104), National Natural Science Foundation of China (51978069), Key Research and Development Plan of Shaanxi Province (2021KWZ-09 and 2021GY-184), the Fundamental Research Funds for the Central Universities, CHD (300102342202), and Science and Technology Planning Project of the Communications Department of Shandong Province (2019B32).
References
Barber, E. S. 1957. “Calculation of maximum pavement temperatures from weather reports.” Highway Res. Board Bull. 168 (May): 1–8.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Chen, J.-Q., H. Wang, and P.-Y. Xie. 2019. “Pavement temperature prediction: Theoretical models and critical affecting factors.” Appl. Therm. Eng. 158 (Jul): 113755. https://doi.org/10.1016/j.applthermaleng.2019.113755.
Chen, T., and C. Guestrin. 2016. “XGBoost: A scalable tree boosting system.” In Proc., 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 785–794. Bootle, UK: Office for Nuclear Regulation. https://doi.org/10.1145/2939672.2939785.
Chen, Z., and W. Fan. 2021. “A freeway travel time prediction method based on an XGBoost model.” Sustainability 13 (15): 8577. https://doi.org/10.3390/su13158577.
Crevier, L.-P., and Y. Delage. 2001. “METRo: A new model for road-condition forecasting in Canada.” J. Appl. Meteorol. 40 (11): 2026–2037. https://doi.org/10.1175/1520-0450(2001)040%3C2026:MANMFR%3E2.0.CO;2.
Dong, T.-X. 2018. Study on spatial and temporal distribution of low temperature and prewarning models for expressway roads in Jiangsu Province. Nanjing, China: Nanjing Univ. of Information Science & Technology.
Fan, G.-F., W.-S. Wang, and C. Liu. 2008. “Artificial neural network based wind power short term prediction system.” Power Syst. Technol. 32 (22): 72–76.
Gao, J.-X., X.-M. Gao, and H.-Y. Yang. 2020. “Short-term traffic flow prediction based on time-space characteristics.” In Proc., 2020 IEEE 5th Int. Conf. on Intelligent Transportation Engineering (ICITE). New York: IEEE. https://doi.org/10.1109/ICITE50838.2020.9231429.
Hochreiter, S., and J. Schmidhuber. 1997. “Long short-term memory.” Neural Comput. 9 (8): 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735.
Hu, J.-C., Z.-J. Lin, and T. Cheng. 2020. “Research progress on temperature prediction method for road icing.” Sci. Technol. Eng. 20 (1): 6.
Jing, C., and J.-X. Zhang. 2018. “Prediction model for asphalt pavement temperature in high-temperature season in Beijing.” Adv. Civ. Eng. 2018 (Jul): 1837952. https://doi.org/10.1155/2018/1837952.
Juga, I., P. Nurmi, and M. Hippi. 2013. “Statistical modelling of wintertime road surface friction.” Meteorol. Appl. 20 (3): 318–329. https://doi.org/10.1002/met.1285.
Kangas, M., M. Heikinheimo, and M. Hippi. 2015. “RoadSurf: A modelling system for predicting road weather and road surface conditions.” Meteorol. Appl. 22 (3): 544–553. https://doi.org/10.1002/met.1486.
Kršmanc, R., A. Š. Slak, and J. Demšar. 2013. “Statistical approach for forecasting road surface temperature.” Meteorol. Appl. 20 (4): 439–446. https://doi.org/10.1002/met.1305.
Lai, G.-K., W.-C. Chang, Y.-M. Yang, and H.-X. Liu. 2018. “Modeling long- and short-term temporal patterns with deep neural networks.” In Proc., 41st Int. ACM SIGIR Conf. on Research & Development in Information Retrieval, 95–104. New York: Association for Computing Machinery. https://doi.org/10.1145/3209978.3210006.
Li, C.-C., Y.-Y. Tang, T. Ge, and Z.-Y. Guo. 2012. Safety management and guarantee technology of highway operation under severe weather conditions. Beijing: China Communications Press.
Li, Y.-Y., J.-Q. Chen, H.-C. Dan, and H. Wang. 2022. “Probability prediction of pavement surface low temperature in winter based on Bayesian structural time series and neural network.” Cold Reg. Sci. Technol. 194 (Feb): 103434. https://doi.org/10.1016/j.coldregions.2021.103434.
Liu, B., S. Yan, H.-L. You, Y. Dong, Y. Li, J.-L. Lang, and R.-T. Gu. 2018. “Road surface temperature prediction based on gradient extreme learning machine boosting.” Comput. Ind. 99 (Aug): 294–302. https://doi.org/10.1016/j.compind.2018.03.026.
Liu, M., D.-P. Yin, Q.-L. Wang, and P. Gao. 2007. “Weather standard and forecast study on winter icing on the road in Nanjing.” Sci. Meteorol. Sin. 27 (6): 685–690.
Liu, X.-M., Y.-C. Yu, and G.-L. Lei. 2004. “Using radiant balance theory to calculate concrete road-surface temperature in summer.” J. Appl. Meteorol. Sci. 15 (5): 623–628.
Ma, N., Y.-R. Chen, W.-L. Wu, N. Cao, and J. Yang. 2015. “Analysis on the variation of road surface highest temperature on Ningxia section of Fu-Yin freeway in the summer and the establishment of its forecast model.” J. Ningxia Univ. 36 (4): 392–399.
Ma, Y. 2018. “Research and analysis on the forecasting of the monthly electricity sales based on the optimal combination method.” M.S. thesis, Dept. of Electrical Engineering, Yanshan Univ.
Qin, J., and L.-J. Sun. 2005. “Review of temperature estimation methods for asphalt pavement in foreign countries.” J. China Foreign Highway 25 (6): 5.
Qin, J., and L.-J. Sun. 2006. “Study on asphalt pavement temperature field distribution pattern.” J. Highway Transp. Res. Dev. 23 (8): 18–21.
Shao, J., J.-Q. Wang, X.-X. Yu, and G.-Y. Tang. 2022. “Features and development of China’s highway investment policy.” In Proc., 2022 Int. Conf. on Urban Planning and Regional Economy (UPRE 2022). Amsterdam, Netherlands: Atlantis Press. https://doi.org/10.2991/aebmr.k.220502.045.
Solmaz, O., M. Ozgoren, and M. H. Aksoy. 2014. “Hourly cooling load prediction of a vehicle in the southern region of Turkey by artificial neural network.” Energy Convers. Manage. 82 (Jun): 177–187. https://doi.org/10.1016/j.enconman.2014.03.017.
Sreedhar, S., and K. P. Biligiri. 2016. “Development of pavement temperature predictive models using thermophysical properties to assess urban climates in the built environment.” Sustainable Cities Soc. 22 (Apr): 78–85. https://doi.org/10.1016/j.scs.2016.01.012.
Sun, G.-L. 2022. “Discussion on traffic safety control technology of high impact section of expressway in severe weather.” Road Traffic Manage. 8: 3.
Tabrizi, S. E., K. Xiao, J. V. G. Thé, M. Saad, H. Farghaly, S. X. Yang, and B. Gharabaghi. 2021. “Hourly road pavement surface temperature forecasting using deep learning models.” J. Hydrol. 603 (Part A): 126877. https://doi.org/10.1016/j.jhydrol.2021.126877.
Tan, H.-W., Q.-L. Yang, J.-C. Xing, K.-F. Huang, S. Zhao, and H.-Y. Hu. 2022. “Photovoltaic power prediction based on combined XGBoost-LSTM model.” Acta Energiae Solaris Sin. 43 (8): 75. https://doi.org/10.19912/j.0254-0096.tynxb.2021-0005.
Tan, Z.-M., Z.-J. Ma, and X.-L. Zou. 2013. “Pavement temperature estimation model based on field temperature data.” J. Tongji Univ. 41 (5): 700–704.
Tang, J.-J., L.-L. Zheng, C.-Y. Han, F. Liu, and J.-M. Cai. 2020. “Traffic incident clearance time prediction and influencing factor analysis using extreme gradient boosting model.” J. Adv. Transp. 2020 (Jun): 6401082. https://doi.org/10.1155/2020/6401082.
Tang, Y.-Y., and Z.-Y. Guo. 2017. “Pavement temperature short-impending prediction based on ARIMA in Winter.” J. Tongji Univ. 45 (12): 6.
Tian, R.-Y., and X.-C. Wei. 2021. “Study on the relationship between the low temperature field of surface layer of asphalt pavement and meteorological factors in the permafrost regions.” Plateau Sci. Res. 5 (1): 9.
Toraldo, E., E. Mariani, S. Alberti, and M. Crispino. 2015. “Experimental investigation into the thermal behavior of wearing courses for road pavements due to environmental conditions.” Constr. Build. Mater. 98 (Nov): 846–852. https://doi.org/10.1016/j.conbuildmat.2015.08.047.
Utku, A., and S. K. Kaya. 2022. “Multi-layer perceptron based transfer passenger flow prediction in Istanbul transportation system.” Dec. Making: Appl. Manage. Eng. 5 (1): 208–224. https://doi.org/10.31181/dmame0315052022u.
Vanichrujee, U., T. Horanont, W. Pattara-atikom, T. Theeramunkong, and T. Shinozaki. 2018. “Taxi demand prediction using ensemble model based on RNNS and XGBoost.” In Proc., 2018 Int. Conf. on Embedded Systems and Intelligent Technology & Int. Conf. on Information and Communication Technology for Embedded Systems (ICESIT-ICICTES). Bangkok, Thailand: Thailand Advanced Institute of Science and Technology. https://doi.org/10.1109/ICESIT-ICICTES.2018.8442063.
Wang, J., and C.-Y. Guo. 2017. “Temperature variation characteristics and prediction model of winter highway pavement in inner Mongolia section of G6 expressway.” In Proc., 34th Annual Meeting of China Meteorological Society. Berlin: Springer.
Wu, G.-C., and T.-Q. Ling. 1998. “The analysis of developing mechanism of thermal crack of the semi-rigid roadbase.” China J. Highway Transp. 11 (1): 21–28.
Wu, S.-B., Z.-G. Chen, and R. Huang. 2016. “An improved ID3 algorithm based on correlation coefficients.” Comput. Eng. Sci. 38 (11): 2342–2347. https://doi.org/10.3969/j.issn.1007-130X.2016.11.028.
Xu, B., H.-C. Dan, and L. Li. 2017. “Temperature prediction model of asphalt pavement in cold regions based on an improved BP neural network.” Appl. Therm. Eng. 120 (Jun): 568–580. https://doi.org/10.1016/j.applthermaleng.2017.04.024.
Xu, H.-N., R. Zhang, Y.-Q. Tan, and X. Bian. 2013. “Temperature distribution of pavement in seasonally frozen regions in winter.” China J. Highway Transp. 26 (2): 7.
Yan, O., P. Xiang, X.-C. Zhou, L. Ye, R. Yi, and S. Daquan. 2013. “Review on icing detection techniques of pavement.” High Way 4: 191–195.
Yan, Z.-R. 1984. “Temperature field analysis of layered pavement system.” J. Tongji Univ. 3: 79–88.
Yang, X.-X., Y.-J. Zou, and L. Chen. 2022. “Operation analysis of freeway mixed traffic flow based on catch-up coordination platoon.” Accid. Anal. Prev. 175 (Sep): 106780. https://doi.org/10.1016/j.aap.2022.106780.
Zhang, N.-J., N.-X. Liang, and Y.-P. Zhu. 2011. “Influence of meteorological elements on temperature field of asphalt pavement.” J. Chongqing Jiaotong Univ. 30 (6): 1327.
Zhang, X., Y. Hao, J. Liang, L.-J. Pan, J.-J. Shen, and S. Lu. 2019. “Characteristics of road surface temperature of Shaanxi expressway and its prediction model.” J. Arid Meteorol. 37 (6): 1028.
Zhang, Y., X.-P. Shi, S. Zhang, and A. Abraham. 2022. “A XGBoost-based lane change prediction on time series data using feature engineering for autopilot vehicles.” IEEE Trans. Intell. Transp. Syst. 23 (10): 19187–19200. https://doi.org/10.1109/TITS.2022.3170628.
Zou, Y.-J., L.-S. Ding, H. Zhang, T. Zhu, and L.-T. Wu. 2022. “Vehicle acceleration prediction based on machine learning models and driving behavior analysis.” Appl. Sci. 12 (10): 5259. https://doi.org/10.3390/app12105259.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 149 • Issue 7 • July 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Sep 7, 2022
Accepted: Mar 8, 2023
Published online: May 12, 2023
Published in print: Jul 1, 2023
Discussion open until: Oct 12, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.