Surface Temperature Prediction of Asphalt Pavement Based on GBDT

Abstract

Asphalt is a temperature sensitive material, distribution characteristics and vary rules of asphalt pavement temperature have an important impact on the bearing capacity and performance of pavement, which is a concern of domestic and foreign researchers. The objective of this study was to explore the correlation between pavement temperature of asphalt pavements and meteorological factors and implement an accurate trend prediction of the asphalt pavement temperature. First, errors and missing data in the meteorological dataset were cleaned. Then, the three kinds of temperature prediction models of asphalt pavements in winter were established by Gradient Boosting Decision Tree (GBDT), Random Forest (RF) and Linear Regression (LR). The results indicate that GBDT would perform an excellent ability on prediction. The mean-square-error of the GBDT predicting results has a lower value of 1.5 when compared with the Random Forest and Linear Regression owing to the high robustness and the good generalization ability, which reflects the GBDT model has a good applicability in the field of prediction. The research would serve as a technical support for the machine learning algorithms applied in the field of the application of prediction problems.