Improved Forecasting of CO2 Emissions Based on an ANN and Multiresolution Decomposition
The sustainability of the environment is a shared goal of the United Nations. In this context, the forecast of environmental variables such as carbon dioxide (CO2) plays an important role for the effective decision making. In this work, it is presented multi-step-ahead forecasting of the CO2 emissions by means of a hybrid model which combines multiresolution decomposition via stationary wavelet transform (SWT) and an artificial neural network (ANN) to improve the accuracy of a typical neural network. The effectiveness of the proposed hybrid model SWT-ANN is evaluated through the time series of CO2 per capita emissions of the Andean Community (CAN) countries from 1996 to 2013. The empirical results provide significant evidence about the effectiveness of the proposed hybrid model to explain these phenomena. Projections are presented for supporting the environmental management of countries with similar geographical features and cultural diversity.
KeywordsCarbon dioxide Multiresolution decomposition Stationary wavelet transform Artificial neural network Forecasting
Thanks to Animal Production and Industrialization (PROANIN) Research Group of the Universidad Nacional de Chimborazo for supporting this work through the project Artificial Neural Networks to predict the carcass tissue composition of guinea pigs.