Articles | Volume 19, issue 18
https://doi.org/10.5194/gmd-19-9035-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-19-9035-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
24 Sep 2026
Development and technical paper |
| 24 Sep 2026
| 24 Sep 2026
A hybrid method for winter road surface temperature prediction using improved LSTMs and stacking-based ensemble learning
Wanting Li
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Center for Applied Mathematics of Jiangsu Province, Nanjing University of Information Science and Technology, Nanjing 210044, China
Jiangsu International Joint Laboratory on System Modelling and Data Analysis, Nanjing University of Information Science and Technology, Nanjing 210044, China
Linyi Zhou
CORRESPONDING AUTHOR
Nanjing Innovation Institute for Atmospheric Sciences, Chinese Academy of Meteorological Sciences – Jiangsu Meteorological Service, Nanjing 210041, China
Jiangsu Key Laboratory of Transportation Meteorology of CMA/Key Laboratory of Severe Storm Disaster Risk, Nanjing 210041, China
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Center for Applied Mathematics of Jiangsu Province, Nanjing University of Information Science and Technology, Nanjing 210044, China
Jiangsu International Joint Laboratory on System Modelling and Data Analysis, Nanjing University of Information Science and Technology, Nanjing 210044, China
Yuanhong Guan
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Center for Applied Mathematics of Jiangsu Province, Nanjing University of Information Science and Technology, Nanjing 210044, China
Jiangsu International Joint Laboratory on System Modelling and Data Analysis, Nanjing University of Information Science and Technology, Nanjing 210044, China
Yuanhao Guo
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Kun Chen
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Weiqi Huang
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Wenqian Zhao
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China
Cited articles
Abo-Hashema, M. A.: Modeling pavement temperature prediction using artificial neural networks, in: Airfield and highway pavement 2013: Sustainable and efficient pavements, American Society of Civil Engineers, Reston, VA, USA, 490–505, https://doi.org/10.1061/9780784413005.039, 2013.
Adwan, I., Milad, A., Memon, Z. A., Widyatmoko, I., Zanuri, N. A., Memon, N. A., and Yusoff, N. I. M.: Asphalt pavement temperature prediction models: A review, Appl. Sci., 11, 3794, https://doi.org/10.3390/app11093794, 2021.
Asefzadeh, A., Hashemian, L., and Bayat, A.: Development of statistical temperature prediction models for a test road in Edmonton, Alberta, Canada, Int. J. Pavement Res. Technol., 10, 369–382, https://doi.org/10.1016/j.ijprt.2017.05.003, 2017.
Athukorallage, B., Senadheera, S., and James, D.: Temporal and spatial temperature predictions for flexible pavement layers using numerical thermal analysis and verified with large datasets, Case Stud. Constr. Mater., 18, e02008, https://doi.org/10.1016/j.cscm.2023.e02008, 2023.
Ayasrah, U. B., Tashman, L., AlOmari, A., and Asi, I.: Development of a temperature prediction model for flexible pavement structures, Case Stud. Constr. Mater., 18, e01697, https://doi.org/10.1016/j.cscm.2022.e01697, 2023.
Ba, J. L., Kiros, J. R., and Hinton, G. E.: Layer normalization, arXiv [preprint], https://doi.org/10.48550/arXiv.1607.06450, 2016.
Bai, S., Yang, W., Zhang, M., Liu, D., Li, W., and Zhou, L.: Attention-based BiLSTM model for pavement temperature prediction of asphalt pavement in winter, Atmosphere, 13, 1524, https://doi.org/10.3390/atmos13091524, 2022.
Ben Taieb, S., Bontempi, G., Atiya, A. F., and Sorjamaa, A.: A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition, Expert Syst. Appl., 39, 7067–7083, https://doi.org/10.1016/j.eswa.2012.01.039, 2012.
Bishop, C. M., Nasrabadi, N. M.: Pattern recognition and machine learning, New York, Springer, https://doi.org/10.1080/15228053.2019.1632410, 2006.
Breiman, L.: Bagging predictors, Mach. Learn., 24, 123–140, https://doi.org/10.1007/BF00058655, 1996.
Chen, J., Wang, H., and Xie, P.: Pavement temperature prediction: Theoretical models and critical affecting factors, Appl. Therm. Eng., 158, 113755, https://doi.org/10.1016/j.applthermaleng.2019.113755, 2019.
Cheng, H., Liu, J., Sun, L., and Liu, L.: Critical position of fatigue damage within asphalt pavement considering temperature and strain distribution, Int. J. Pavement Eng., 22, 1773–1784, https://doi.org/10.1080/10298436.2020.1724288, 2021.
China Meteorological Administration: Grade of highway traffic high-impact weather warning, QX/T 414-2018, China Meteorological Press, Beijing, China, 2018.
Crevier, L.-P. and Delage, Y.: METRo: A new model for road-condition forecasting in Canada, J. Appl. Meteorol., 40, 2026–2037, https://doi.org/10.1175/1520-0450(2001)040<2026:MANMFR>2.0.CO;2, 2001.
Dai, B., Yang, W., Ji, X., and Zhou, L.: An ensemble deep learning model for short-term road surface temperature prediction, J. Transp. Eng. B-Pavements, 149, 04022067, https://doi.org/10.1061/JPEODX.PVENG-1192, 2023.
Darghiasi, P., Baral, A., Mattingly, S., and Shahandashti, M.: Estimation of road surface temperature using NOAA gridded forecast weather data for snowplow operations management, J. Cold Reg. Eng., 37, 04023018, https://doi.org/10.1061/JCRGEI.CRENG-691, 2023.
Darghiasi, P., Zamanian, M., and Shahandashti, M.: Enhancing Winter Maintenance Decision Making through Deep Learning-Based Road Surface Temperature Estimation, in: Construction Res. Congr. 2024, ASCE, 701–711, https://doi.org/10.1061/9780784485262.70, 2024.
Darghiasi, P., Zamanian, M., Bhatta, S., and Shahandashti, M.: Enhanced road surface temperature prediction using random forest model and NWS weather forecast data, in: International Conference on Transportation and Development 2025, American Society of Civil Engineers, Reston, VA, USA, 286–298, https://doi.org/10.1061/9780784486191.025, 2025.
Diefenderfer, B. K., Al-Qadi, I. L., and Diefenderfer, S. D.: Model to predict pavement temperature profile: development and validation, J. Transp. Eng., 132, 162–167, https://doi.org/10.1061/(ASCE)0733-947X(2006)132:2(162), 2006.
Divina, F., Gilson, A., Gómez-Vela, F., García Torres, M., and Torres, J. F.: Stacking ensemble learning for short-term electricity consumption forecasting, Energies, 11, 949, https://doi.org/10.3390/en11040949, 2018.
Feng, T. and Feng, S.: A numerical model for predicting road surface temperature in the highway, Procedia Engineer., 37, 137–142, https://doi.org/10.1016/j.proeng.2012.04.216, 2012.
Gedafa, D. S., Hossain, M., and Romanoschi, S. A.: Perpetual pavement temperature prediction model, Road Mater. Pavement Des., 15, 55–65, https://doi.org/10.1080/14680629.2013.852610, 2014.
Gelman, A. and Shalizi, C. R.: Philosophy and the practice of Bayesian statistics, Brit. J. Math. Stat. Psy., 66, 8–38, https://doi.org/10.1111/j.2044-8317.2011.02037.x, 2013.
Ghalandari, T., Shi, L., Sadeghi-Khanegah, F., Van den Bergh, W., and Vuye, C.: Utilizing artificial neural networks to predict the asphalt pavement profile temperature in western Europe, Case Stud. Constr. Mater., 18, e02130, https://doi.org/10.1016/j.cscm.2023.e02130, 2023.
Glorot, X., Bordes, A., and Bengio, Y.: Deep sparse rectifier neural networks, in: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research (PMLR), 15, 315–323, 2011.
Gui, J., Phelan, P. E., Kaloush, K. E., and Golden, J. S.: Impact of pavement thermophysical properties on surface temperatures, J. Mater. Civil Eng., 19, 683–690, https://doi.org/10.1061/(ASCE)0899-1561(2007)19:8(683), 2007.
Hassan, H. F., Al-Nuaimi, A. S., Taha, R., and Jafar, T. M.: Development of asphalt pavement temperature models for Oman, J. Eng. Res., 2, 32–42, https://doi.org/10.24200/tjer.vol2iss1pp32-42, 2005.
Hatamzad, M., Pinerez, G. C. P., and Casselgren, J.: Intelligent cost-effective winter road maintenance by predicting road surface temperature using machine learning techniques, Knowl.-Based Syst., 247, 108682, https://doi.org/10.1016/j.knosys.2022.108682, 2022.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Piscataway, NJ, USA, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
Hermansson, Å.: Mathematical model for paved surface summer and winter temperature: comparison of calculated and measured temperatures, Cold Reg. Sci. Technol., 40, 1–17, https://doi.org/10.1016/j.coldregions.2004.01.002, 2004.
Hochreiter, S. and Schmidhuber, J.: Long short-term memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Hoerl, A. E. and Kennard, R. W.: Ridge regression: Biased estimation for nonorthogonal problems, Technometrics, 12, 55–67, https://doi.org/10.1080/00401706.1970.10488634, 1970.
Jing, C. and Zhang, J.: Prediction model for asphalt pavement temperature in high‐temperature season in Beijing, Adv. Civ. Eng., 2018, 1837952, https://doi.org/10.1155/2018/1837952, 2018.
Joo, C., Park, H., Lim, J., Cho, H., and Kim, J.: Learning-based heat deflection temperature prediction and effect analysis in polypropylene composites using catboost and shapley additive explanations, Eng. Appl. Artif. Intel., 126, 106873, https://doi.org/10.1016/j.engappai.2023.106873, 2023.
Kangas, M., Heikinheimo, M., and Hippi, M.: RoadSurf: a behaviour system for predicting road weather and road surface conditions, Meteorol. Appl., 22, 544–553, https://doi.org/10.1002/met.1486, 2015.
Karsisto, V., Nurmi, P., Kangas, M., Hippi, M., and Uppala, A.: Improving road weather model forecasts by adjusting the radiation input, Meteorol. Appl., 23, 503–513, https://doi.org/10.1002/met.1574, 2016.
Kebede, Y. B., Yang, M. D., and Huang, C. W.: Real-time pavement temperature prediction through ensemble machine learning, Eng. Appl. Artif. Intel., 135, 108870, https://doi.org/10.1016/j.engappai.2024.108870, 2024.
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 2014.
Kršmanc, R., Slak, A. Š., and Demšar, J.: Statistical approach for forecasting road surface temperature, Meteorol. Appl., 20, 439–446, https://doi.org/10.1002/met.1305, 2013.
Kuncheva, L. I. and Whitaker, C. J.: Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy, Mach. Learn., 51, 181–207, https://doi.org/10.1023/a:1022859003006, 2003.
Li, W.: A hybrid method for winter road surface temperature prediction using improved LSTMs and stacking-based ensemble learning, Zenodo [code, data set], https://doi.org/10.5281/zenodo.22020890, 2026.
Li, Y., Liu, L., and Sun, L.: Temperature predictions for asphalt pavement with thick asphalt layer, Constr. Build. Mater., 160, 802–809, https://doi.org/10.1016/j.conbuildmat.2017.11.077, 2018.
Li, Y., Chen, J., Dan, H., and Wang, H.: Probability prediction of pavement surface low temperature in winter based on bayesian structural time series and neural network, Cold Reg. Sci. Technol., 194, 103434, https://doi.org/10.1016/j.coldregions.2021.103434, 2022.
Lin, M., Chen, Q., and Yan, S.: Network in network, arXiv [preprint], https://doi.org/10.48550/arXiv.1312.4400, 2013.
Liu, B., Yan, S., You, H., Dong, Y., Li, Y., Lang, J., and Gu, R.: Road surface temperature prediction based on gradient extreme learning machine boosting, Comput. Ind., 99, 294–302, https://doi.org/10.1016/j.compind.2018.03.026, 2018.
Lundberg, S. M. and Lee, S. I.: A unified approach to interpreting model predictions, Adv. Neur. In., arXiv [preprint], https://doi.org/10.48550/arXiv.1705.07874, 2017.
Luo, X., Li, D., Yang, Y., and Zhang, S.: Spatiotemporal traffic flow prediction with KNN and LSTM, J. Adv. Transp., 2019, 4145353, https://doi.org/10.1155/2019/4145353, 2019.
MacKay, D. J. C.: Bayesian interpolation, Neural Comput., 4, 415–447, https://doi.org/10.1162/neco.1992.4.3.415, 1992.
Maddu, R., Vanga, A. R., Sajja, J. K., Basha, G., and Shaik, R.: Prediction of land surface temperature of major coastal cities of India using bidirectional LSTM neural networks, J. Water Clim. Change, 12, 3801–3819, https://doi.org/10.2166/wcc.2021.460, 2021.
Milad, A., Adwan, I., Majeed, S. A., Yusoff, N. I. M., Al-Ansari, N., and Yaseen, Z. M.: Emerging technologies of deep learning models development for pavement temperature prediction, IEEE Access, 9, 23840–23849, https://doi.org/10.1109/ACCESS.2021.3056568, 2021a.
Milad, A. A., Adwan, I., Majeed, S. A., Memon, Z. A., Bilema, M., and Omar, H. A.: Development of a hybrid machine learning model for asphalt pavement temperature prediction, IEEE Access, 9, 158041–158056, https://doi.org/10.1109/ACCESS.2021.3129979, 2021b.
Minhoto, M. J. C., Pais, J. C., Pereira, P. A., and Picado-Santos, L.: Predicting asphalt pavement temperature with a three-dimensional finite element method, Transp. Res. Rec., 1919, 96–110, https://doi.org/10.1177/0361198105191900111, 2005.
Molavi Nojumi, M., Huang, Y., Hashemian, L., and Bayat, A.: Application of machine learning for temperature prediction in a test road in Alberta, Int. J. Pavement Res. Technol., 15, 303–319, https://doi.org/10.1007/s42947-021-00023-3, 2022.
Muñoz Sabater, J.: ERA5-Land hourly data from 1950 to present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS) [data set], https://doi.org/10.24381/cds.e2161bac, 2019.
Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., Hersbach, H., Martens, B., Miralles, D. G., Piles, M., Rodríguez-Fernández, N. J., Zsoter, E., Buontempo, C., and Thépaut, J.-N.: ERA5-Land: a state-of-the-art global reanalysis dataset for land applications, Earth Syst. Sci. Data, 13, 4349–4383, https://doi.org/10.5194/essd-13-4349-2021, 2021.
Nantasai, B. and Nassiri, S.: Winter temperature prediction for near-surface depth of pervious concrete pavement, Int. J. Pavement Eng., 20, 820–829, https://doi.org/10.1080/10298436.2017.1353389, 2019.
Nowrin, T. and Kwon, T. J.: Forecasting short-term road surface temperatures considering forecasting horizon and geographical attributes–an ANN-based approach, Cold Reg. Sci. Technol., 202, 103631, https://doi.org/10.1016/j.coldregions.2022.103631, 2022.
Qin, Y. and Hiller, J. E.: Ways of formulating wind speed in heat convection significantly influencing pavement temperature prediction, Heat Mass Transfer, 49, 745–752, https://doi.org/10.1007/s00231-013-1116-0, 2013.
Qin, Y., Zhang, X., Tan, K., and Wang, J.: A review on the influencing factors of pavement surface temperature, Environ. Sci. Pollut. R., 29, 67659–67674, https://doi.org/10.1007/s11356-022-22295-3, 2022.
Qiu, X., Hong, H., Xu, W., Yang, Q., and Xiao, S.: Surface temperature prediction of asphalt pavement based on APRIORI-GBDT, in: International Conference on Transportation and Development 2020, 200–212, https://doi.org/10.1061/9780784483183.020, 2020.
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., and Prabhat, F.: Deep learning and process understanding for data-driven Earth system science, Nature, 566, 195–204, https://doi.org/10.1038/s41586-019-0912-1, 2019.
Rigabadi, A., Rezaei Zadeh Herozi, M., and Rezagholilou, A.: An attempt for development of pavements temperature prediction models based on remote sensing data and artificial neural network, Int. J. Pavement Eng., 23, 2912–2921, https://doi.org/10.1080/10298436.2021.1873334, 2022.
Saliko, D., Ahmed, A., and Erlingsson, S.: Development and validation of a pavement temperature profile prediction model in a mechanistic-empirical design framework, Transp. Geotech., 40, 100976, https://doi.org/10.1016/j.trgeo.2023.100976, 2023.
Schindler, A. K., Ruiz, J. M., Rasmussen, R. O., Chang, G. K., and Wathne, L. G.: Concrete pavement temperature prediction and case studies with the FHWA HIPERPAV models, Cem. Concr. Compos., 26, 463–471, https://doi.org/10.1016/s0958-9465(03)00075-1, 2004.
Schuster, M. and Paliwal, K. K.: Bidirectional recurrent neural networks, IEEE T. Signal Proces., 45, 2673–2681, https://doi.org/10.1109/78.650093, 1997.
Shao, J. and Lister, P. J.: An automated nowcasting model of road surface temperature and state for winter road maintenance, J. Appl. Meteorol., 35, 1352–1361, https://doi.org/10.1175/1520-0450(1996)035<1352:AANMOR>2.0.CO;2, 1996.
Song, P., Che, J., and Guo, T.: Climatic characteristics and SVM forecast model of subfreezing road temperature on expressways, J. Mar. Meteorol., 29, 56–64, https://doi.org/10.19513/j.cnki.issn2096-3599.2023.03.008, 2023.
Spearman, C.: The proof and measurement of association between two things, in: Studies in Individual Differences: The Search for Intelligence, edited by: Jenkins, J. J. and Paterson, D. G., Appleton-Century-Crofts, New York, NY, USA, 45–58, https://doi.org/10.1037/11491-005, 1961.
Tabrizi, S. E., Xiao, K., Thé, J. V. G., Saad, M., Farghaly, H., Yang, S. X., and Gharabaghi, B.: Hourly road pavement surface temperature forecasting using deep learning models, J. Hydrol., 603, 126877, https://doi.org/10.1016/j.jhydrol.2021.126877, 2021.
Tao, R., Peng, R., Wang, H., Wang, J., and Qiao, J.: Temperature and humidity prediction of mountain highway tunnel entrance road surface based on improved Bi-LSTM neural network, Evol. Syst., 15, 691–702, https://doi.org/10.1007/s12530-023-09538-5, 2024.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I.: Attention is all you need, Adv. Neur. In., 30, https://doi.org/10.1201/9781003561460-19, 2017.
Wang, D.: Simplified analytical approach to predicting asphalt pavement temperature, J. Mater. Civil Eng., 27, 04015043, https://doi.org/10.1061/(ASCE)MT.1943-5533.0001301, 2015.
Wang, D., Roesler, J. R., and Guo, D. Z.: Analytical approach to predicting temperature fields in multilayered pavement systems, J. Eng. Mech., 135, 334–344, https://doi.org/10.1061/(ASCE)0733-9399(2009)135:4(334), 2009.
Wang, X., Pan, P., and Li, J.: Real-time measurement on dynamic temperature variation of asphalt pavement using machine learning, Measurement, 207, 112413, https://doi.org/10.1016/j.measurement.2022.112413, 2023.
Wolpert, D. H.: Stacked generalization, Neural Netw., 5, 241–259, https://doi.org/10.1016/S0893-6080(05)80023-1, 1992.
Yang, C. H., Yun, D. G., Kim, J. G., Lee, G., and Kim, S. B.: Machine learning approaches to estimate road surface temperature variation along road section in real-time for winter operation, Int. J. Intell. Transp. Syst. Res., 18, 343–355, https://doi.org/10.1007/s13177-019-00198-x, 2020.
Yin, Z., Hadzimustafic, J., Kann, A., and Wang, Y.: On statistical nowcasting of road surface temperature, Meteorol. Appl., 26, 1–13, https://doi.org/10.1002/met.1737, 2019.
Yuan, J., Cheng, H., Sun, L., Cao, Y., Yang, R., Jin, T., and Li, M.: Cross-Regional Pavement Temperature Prediction Using Transfer Learning and Random Forest, Appl. Sci., 15, 7436, https://doi.org/10.3390/app15137436, 2025.
Zhang, M., Guo, H., Li, J. Y., Li, L., and Zhu, F.: A deep learning approach for enhanced real-time prediction of winter road surface temperatures in high-altitude mountain areas, Promet, 36, 958–972, https://doi.org/10.7307/ptt.v36i5.541, 2024.
Zhang, N., Mao, T., Chen, H., Lv, L., Wang, Y., and Yan, Y.: Temperature prediction for expressway pavement icing in winter based on XGBoost–LSTNet variable weight combination model, J. Transp. Eng. A-Syst., 149, 04023062, https://doi.org/10.1061/JTEPBS.TEENG-7918, 2023.
Zhao, X., Shen, A., and Ma, B.: Temperature response of asphalt pavement to low temperatures and large temperature differences, Int. J. Pavement Eng., 21, 49–62, https://doi.org/10.1080/10298436.2018.1435877, 2020.
Short summary
Accurate winter road surface temperature prediction prevents icy‑road accidents. Existing methods either need rare pavement parameters or miss local weather patterns and long‑term trends. This study combines two deep‑learning models to analyse four winters of Jiangsu data. It achieves lower prediction errors in general and outperforms common models at 1, 3 and 6 h horizons. Station‑based features beat external reanalysis data.
Accurate winter road surface temperature prediction prevents icy‑road accidents. Existing...
