Most of the primary roads in the United States (US) are constructed using hot-mix asphalt (HMA). The stiffness and rutting performance of HMA are highly dependent on temperature due to the viscoelastic nature of asphalt binder. Thus, it is very important to accurately predict the temperature profile of asphalt surfaces. This work was based on the Asphalt Treated Base-90 (ATB-90) project that is located at the I-90 road in Ashtabula County, Ohio. Temperature probes (TP101) were embedded during construction to monitor the temperature profile within pavement structures. Two weather stations were installed in the project site to collect climatic data that includes air temperature, wind speed, wind direction, rainfall and solar radiation. The data collected from January 2006 to December 2007 at Ohio Department of Transportation (ODOT) section 304 were used to develop the regression models to predict the daily maximum and minimum pavement temperature profiles. On the other hand, the data collected from January 2008 through December 2008 at ODOT sections 304 and 307 Iowa (IA) were used to validate the developed models. The results indicate that the developed models can predict the daily maximum and minimum pavement temperatures with sufficient accuracy. The adjusted R² and the root mean square error (RMSE) were calculated to be 82.8% and 5.1, respectively for the maximum temperature prediction model and 86.1% and 4.1, respectively for the minimum temperature prediction model.