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.

[1]  P. Pinter,et al.  Productivity and water use of wheat under free‐air CO2 enrichment , 1995 .

[2]  Daniel Svozil,et al.  Introduction to multi-layer feed-forward neural networks , 1997 .

[3]  Mark J. Shensa,et al.  The discrete wavelet transform: wedding the a trous and Mallat algorithms , 1992, IEEE Trans. Signal Process..

[4]  Hiok Chai Quek,et al.  RLDDE: A novel reinforcement learning-based dimension and delay estimator for neural networks in time series prediction , 2007, Neurocomputing.

[5]  H. Pao,et al.  Modeling and forecasting the CO 2 emissions, energy consumption, and economic growth in Brazil , 2011 .

[6]  Ah Chung Tsoi,et al.  Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[7]  Héctor Pomares,et al.  Time series analysis using normalized PG-RBF network with regression weights , 2002, Neurocomputing.

[8]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[9]  A. Grossmann,et al.  DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE , 1984 .

[10]  Fulu Tao,et al.  Effects of climate change, CO2 and O3 on wheat productivity in Eastern China, singly and in combination , 2017 .

[11]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[12]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  B. Silverman,et al.  The Stationary Wavelet Transform and some Statistical Applications , 1995 .

[14]  Rigoberto Pérez-Suárez,et al.  Growing green? Forecasting CO2 emissions with Environmental Kuznets Curves and Logistic Growth Models , 2015 .

[15]  Seok-Beom Roh,et al.  Design of fuzzy radial basis function-based polynomial neural networks , 2011, Fuzzy Sets Syst..

[16]  Sifeng Liu,et al.  Modelling and forecasting CO2 emissions in the BRICS (Brazil, Russia, India, China, and South Africa) countries using a novel multi-variable grey model , 2015 .

[17]  Leslie S. Smith,et al.  A novel neural network ensemble architecture for time series forecasting , 2011, Neurocomputing.

[18]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .