Determining the surface temperature of asphalt based on weather data
DOI:
https://doi.org/10.24228/KTSZ.2026.5.2Keywords:
pavement temperature, machine learning, regression models, temperature forecasting, weather dataAbstract
Pavement temperature has a key importance in road construction, both in the design of the pavement structure and in road maintenance. The in-depth temperature can be determined from the pavement surface temperature, which is an important parameter in design and for deflection measurements. Surface temperature has particular importance to road maintenance engineers during winter operations, as it serves as an indicator for when to begin preventive de-icing. There are approximately 400 weather stations located along the Hungarian national highway network, meaning that a single measuring station characterizes the temperature conditions of 80 km of the road network. In addition to road surface temperature, these stations also collect a variety of other weather data, such as air temperature, relative humidity, wind speed, etc. This article examines regression models based on weather data for predicting surface temperature. Using data from meteorological stations in Hungary, I trained 24 different models. The best model (Matern 5/2 GPR) achieved an accuracy of RMSE = 2.33°C using data at 10-minute intervals, while using hourly inputs improved the model’s accuracy to RMSE = 2.24°C, which can be explained by a reduction in statistical noise. The model optimized by separating the daytime and nighttime data sets did not improve accuracy but did slightly complicate the calculations; therefore, the final model was trained on the aggregated 24-hour data. The article confirms that four meteorological inputs (air temperature, solar radiation, its variation, and water film thickness) are sufficient to achieve this. Other meteorological parameters, such as relative humidity, wind speed, and precipitation intensity, did not improve the model’s accuracy. Simpler models (e.g., a linear regression model, RMSE = 2.88°C) also showed similar overall accuracy; however, their average error increased significantly under extreme temperatures, reaching an RMSE > 4.5°C above 40°C. Therefore, from an engineering perspective, the use of the more complex model is recommended, despite its higher computational demands. Using the presented regression model, the surface temperature of the pavement can be determined based on three measured and one calculated weather data point. This tool makes it possible to determine the pavement temperature even at locations where there is no weather station or where it is located far away, or where the station has not been restored after pavement rehabilitation, or where it is otherwise out of service. In the context of long-term monitoring, this can be important information; until a domestic solution is developed and implemented, the model presented in this article can provide effective assistance to public road operators during winter operations, thereby enhancing traffic safety.
References
Barber, E.S. (1957) Calculation of Maximum Pavement Temperatures From Weather Reports. HRB, National Research Council, Washington D.C., pp. 1-8. URL: http://onlinepubs.trb.org/Onlinepubs/hrbbulletin/168/168-001.pdf
Bland, J. M., Altman D. G. (1986) Statistical methods for assessing agreement between two methods of clinical measurement. Lancet, pp. 307–310. DOI: https://doi.org/10.1016/S0140-6736(86)90837-8
Cho, S., Tóth, Cs. (2022) Temperature estimation method of asphalt pavement in Hungary. FACTA UNIVERSITATIS, Architechture and Civil Engineering, 20(3), pp. 203–212. DOI: https://doi.org/10.2298/FUACE220213016C
Dickinson, J. E. (1978) A method for calculating the temperature gradients in asphaltic concrete pavement structures based on climatic data. Austrian Road Research, 8(4), pp. 16-34.
Dierfenderer, B. K., Al-Qadi, I. L., Dierfenderfer S. D. (2006) Model to predict pavement temperature profile: development and validation. Journal of Transportation Engineering, 132(2), pp. 162-167. DOI: https://doi.org/10.1061/(ASCE)0733-947X(2006)132:2(162)
Herceg, A., Primusz, P., Kalicz, P., Gribovszki, Z. (2020) A klimatikus jellemzők hatásai az útpályaszerkezetre: A pályaszerkezet hőmérsékletek számítása. Útügyi Lapok, 8(14). DOI: https://doi.org/10.36246/UL.2020.2.02
Herceg, A., Tóth, Cs., Primusz, P., Kalicz, P., Gribovszki, Z. (2022) Hazai bitumenek viselkedési fokozatának meghatározása egy soproni tesztparcella meteorológiai adatai alapján. Közlekedéstudományi Szemle, 72(1), pp. 32-47. DOI: https://doi.org/10.24228/KTSZ.2022.1.3
Huang, Y., Nojumi, M. M., Ansari, S., Hashemian, L., Bayat, A. (2024) Multi-depth temperature prediction using machine learning for pavement sections. Journal of Applied Remote Sensoring, 18(1). DOI: https://doi.org/10.1117/1.JRS.18.014517
Kebede, Y. B., Yang, MD., Huang, Ch. W. (2024) Real-time pavement temperature prediction through ensemble machine learning. Engineering Applications of Artificial Intelligence, 135, 108870. DOI: https://doi.org/10.1016/j.engappai.2024.108870
Khan, Z. H., Md Islam, R., Tarefder, R. A. (2019) Determining asphalt surface temperature using weather parameters. Journal of Traffic and Transportation Engineering, 6(6), pp. 577–588. DOI: https://doi.org/10.1016/j.jtte.2018.04.005
Mohseni, A. (1998) LTPP Seasonal Asphalt Concrete (AC) Pavement Temperature Models. FHWA Reports, pp. 1-72. URL: https://rosap.ntl.bts.gov/view/dot/40378
Pethő, L. (2008) A hőmérséklet eloszlás alakulása az aszfalt burkolatú pályaszerkezetekben és ennek hatása a pályaszerkezeti rétegek méretezésére, technológiai tervezésére. PhD értekezés. Budapesti Műszaki és Gazdaságtudományi Egyetem. URL: https://repozitorium.omikk.bme.hu/items/1ab9a912-e4a7-447d-85b2-e91859efa49a
Rasmussen, C. E., Williams, C. K. I. (2006) Gaussian Processes for Machine Learning. Cambridge, MA, The MIT Press. DOI: https://doi.org/10.7551/mitpress/3206.001.0001
Rumney, T. N., Jimenez, R. A. (1969) Pavement Temperatures in the Southwest. Highway Reasearch Record 361, HRB, National Research Council, Washington D.C., pp. 1-13. URL: http://hdl.handle.net/10150/566372
Solaimanian, M., Kennedy, T. W. (1993) Predicting Maximum Pavement Surface temperature Using Maximum Air Temperature and Hourly Solar Radiation. Transportation Research Record, 1417, pp. 1-11. URL: http://onlinepubs.trb.org/Onlinepubs/trr/1993/1417/1417-001.pdf
Schuirmann, D.J. (1987) A comparison of the Two One-Sided Tests Procedure and the Power Approach for assessing the equivalence of average bioavailability. Journal of Pharmacokinetics and Biopharmaceutics 15, pp. 657–680. DOI: https://doi.org/10.1007/BF01068419
Ureczky, J., Tóth, Cs. (2008) A hőmérséklet teherbírásra gyakorolt hatásának vizsgálata. Közúti és mélyépítési szemle, 58(3-4), pp. 9-14. URL: https://szemle.pms2000.hu/docs/2008_3_4.pdf
Vapnik, V. N. (1995) The Nature of Statistical Learning Theory. Springer, New York. DOI: http://dx.doi.org/10.1007/978-1-4757-2440-0
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Koch Domonkos

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published in the journal are licensed under CC-BY-NC-ND 4.0 license. The copyright for submitted manuscripts remains with the author(s).








