Prediction of energy’s environmental impact using a three-variable time series model

作者：

Highlights：

• The purpose of this research is to predict CO2 emission in Taiwan.

• A Three-Variable Time Series Model is proposed to improve the prediction accuracy.

• A comparative analysis is performed between our method and BPN neural network.

• The results show that our method outperforms BPN in terms of MAPE and MASE.

摘要

•The purpose of this research is to predict CO2 emission in Taiwan.•A Three-Variable Time Series Model is proposed to improve the prediction accuracy.•A comparative analysis is performed between our method and BPN neural network.•The results show that our method outperforms BPN in terms of MAPE and MASE.

论文关键词：Multivariate time series analysis,GDP per capita,Renewable energy supplies,CO2 emission,Backpropagation neural network,MAPE,MASE

论文评审过程：Available online 29 July 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.07.074