Temperature is known to be one of the most important factors affecting the design and performance of asphalt concrete pavement. The distresses of asphalt overlay are closely related to its temperature, particularly in Guangxi, a hot-humid-climate region in China. This research is to analyze the impact of meteorological factors on temperature at 2 cm depth in asphalt overlay by ReliefF algorithm and also obtain the temperature prediction model using MATLAB. Two test sites were installed to monitor the temperatures at different pavement depths from 2014 to 2016; meanwhile, the meteorological data (including air temperature, solar radiation, wind speed, and relative humidity) were collected from the two meteorological stations. It has been found that the temperature at 2 cm depth experiences greater temperature variation, and the maximum and minimum temperatures of asphalt overlay, respectively, occur at 2 cm depth and on the surface. Besides, the results of ReliefF algorithm have also shown that the temperature at 2 cm depth is affected significantly by solar radiation, air temperature, wind speed, and the relative humidity. Based on these analyses, the prediction model of maximum temperature at 2 cm depth is developed using statistical regression. Moreover, the data collected in 2017 are used to validate the accuracy of the model. Compared with the existing models, the developed model was confirmed to be more effective for temperature prediction in hot-humid region. In addition, the analysis of rutting depth and overlay deformation for the two test sections with different materials is done, and the results have shown that reasonable structure and materials of asphalt overlay are vital to promote the high-temperature antideforming capability of pavement.
MARSpline model for lead seven-day maximum and minimum air temperature prediction in Chennai, India
