Research on the driving factors of energy carbon footprint in Liaoning province using random forest algorithm

Abstract

Rapid development of economy has obviously promoted the growth of carbon emission, which causes the ecological environment more fragile. How to calculate the energy carbon footprint and explore tradeoff between energy and environment becomes further significance. This study examines energy carbon footprint in Liaoning Province. The main goal of this study is to calculate the energy carbon footprint using random forest algorithm and verify the performance of random forest algorithm. The study first examines factors of energy carbon emissions and implicates calculating method of energy carbon footprint. Subsequently random forest algorithm is developed in calculating energy carbon footprint. The results show that the calculated results of random forest algorithm is close to the actual value and the trend of change is basically similar to the actual value. Furthermore, the performance of random forest algorithm is compared with Partial Least Squares algorithm. The relative error and average relative error of random forest algorithm are both less than Partial Least Squares algorithm.