ABSTRACT
The extreme temperatures experienced by highway pavements significantly impact road traffic, primarily stemming from meteorological disasters such as unusual high air temperatures, snowstorms, and freezing conditions. However, existing approaches fail to adequately account for the influence of meteorological factors. Developing a rational and effective modeling approach is crucial for precise predictions of highway pavement extreme temperatures. Such predictions not only help prevent traffic accidents but also offer reliable decision-making support for road maintenance and traffic management. In this research, we present an efficient short-term prediction model for highway pavement temperatures, based on a multi-layered Gated Recurrent Unit (GRU) framework. This model comprehensively incorporates the impact of meteorological factors on pavement temperatures and is subsequently validated using meteorological data collected from a highway section managed by the Zhaotong District Operation Department of Yunnan Communications Investment & Construction Group CO., LTD. We conduct comparisons across various prediction time intervals and find that the model's optimal performance occurs at a 1.5-hour prediction step, with lowest Mean Absolute Error (MAE), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE) values. Moreover, the experimental outcomes indicate that our proposed model's performance outperforms that of other competing models, including BiGRU-attention, BiLSTM-attention, Muti-RNN, and Muti-LSTM. Our experimental results demonstrate that the method proposed in this study effectively predicts extreme highway pavement temperatures.
- Hatamzad M, Pinerez G C P, Casselgren J. Intelligent cost-effective winter road maintenance by predicting road surface temperature using machine learning techniques. Knowledge Based Systems, 247, 108682, 2022.Google ScholarDigital Library
- Adwan I, Milad A, Memon Z A, Asphalt Pavement Temperature Prediction Models: A Review. Applied Sciences, 11(9), 3794, 2021.Google ScholarCross Ref
- Barber E S. Calculation of maximum pavement temperatures from weather reports. Highway Research Board Bulletin, 168, 1-8, 1957.Google Scholar
- Solaimanian, M, Kennedy T.W. Predicting Maximum Pavement Surface Temperature Using Maximum Air Temperature and Hourly Solar Radiation. Transportation research record 1417, 1-1, 1993.Google Scholar
- Tang J J, Guo Z Y. Pavement Temperature Short-impending Prediction Based on ARIMA in Winter. Journal of Tongji University (Natural Science), 45(12), 1824-1829, 2017.Google Scholar
- Asefzadeh A, Hashemian L, Bayat A. Development of statistical temperature prediction models for a test road in Edmonton, Alberta, Canada. International Journal of Pavement Research and Technology, 10(5), 369-382, 2017.Google ScholarCross Ref
- Kršmanc R, Slak A Š. Statistical approach for forecasting road surface temperature. Meteorological applications, 20(4), 439-446, 2013.Google Scholar
- Yang C.H, Yun D.G, Kim J.G, Machine learning approaches to estimate road surface temperature variation along road section in real-time for winter operation. International Journal of Intelligent Transportation Systems Research, 18, 343-355, 2020.Google ScholarCross Ref
- Molavi Nojumi M, Huang Y, Hashemian L, Application of Machine Learning for Temperature Prediction in a Test Road in Alberta. International Journal of Pavement Research and Technology, 15(2), 303-319, 2022.Google ScholarCross Ref
- Nowrin T, Kwon T J. Forecasting short-term road surface temperatures considering forecasting horizon and geographical attributes-an ANN-based approach. Cold Regions Science and Technology, 202, 103631, 2022.Google ScholarCross Ref
Index Terms
- Highway pavement temperature short-term prediction model based on multi-layer GRU
Recommendations
Comparing ambient temperature account methods in neural network based city short-term load forecasting
We offer a neural network model for forecasting the next day's hourly electric load of a city. We use a few ambient temperature account methods in the research to see how each of them affects the forecasting accuracy. Optimal meta-parameters are ...
An aggregation approach to short-term traffic flow prediction
In this paper, an aggregation approach is proposed for traffic flow prediction that is based on the moving average (MA), exponential smoothing (ES), autoregressive MA (ARIMA), and neural network (NN) models. The aggregation approach assembles ...
Short-Term Traffic Speed Prediction for an Urban Corridor
Short-term traffic speed prediction is one of the most critical components of an intelligent transportation system ITS. The accurate and real-time prediction of traffic speeds can support travellers' route choices and traffic guidance/control. In this ...
Comments