Research on carbon emission prediction method of expressway construction based on XGBoost-SVR combined model
The prediction of expressway carbon emission is an important issue to achieve energy conservation and emission reduction in the field of transportation.14 parameters related to carbon emission of expressway engineering were selected,including subgrade length,pavement area,bridge length,tunnel length,and so on.The life cycle assessment(LCA)method was adopted to calculate the carbon emissions of expressway construction,and 80 carbon emission samples were obtained.The influencing parameters on carbon emission were analyzed.The XGBoost-SVR combined models of machine learning were put forward by equivalent weighting,residual weighting and adaptive weighting.According to the carbon emission samples of expressway,the carbon emission prediction results were obtained by training and learning of XGBoost-SVR combined model.Based on the error and correlation index analysis,the prediction results of three weighted combination models were compared with those of the single machine learning model.The results show that the XGBoost-SVR combined model combines the advantages of XGBoost and SVR model,and its prediction effect is significantly better than that of single machine learning model.Compared with equivalent weighting,residual weighting and adaptive weighting,the XGBoost-SVR model based on adaptive weighting presents the highest prediction accuracy,and it is recommended to be applied in the carbon emission prediction of expressway construction.
万方数据
维普
