Forecasting GHG emissions using an optimized artificial neural network model based on correlation and principal component analysis
Abstract
The prediction of GHG emissions is very important due to their negative impacts on climate and global warming. The aim of this study was to develop a model for GHG forecasting emissions at the national level using a new approach based on artificial neural networks (ANN) and broadly available sustainability, economical and industrial indicators acting as inputs. The ANN model architecture and training parameters were optimized, with inputs being selected using correlation analysis and principal component analysis. The developed ANN models were compared with the corresponding multiple linear regression (MLR) model, while an ANN model created using transformed inputs (principal components) was compared with a principal component regression (PCR) model. Since the best results were obtained with the ANN model based on correlation analysis, that particular model was selected for the actual 2011 GHG emissions forecasting. The relative errors of the 2010 GHG emissions predictions were used to ...adjust the ANN model predictions for 2011, which subsequently resulted in the adjusted 2011 predictions having a MAPE value of only 3.60%. Sensitivity analysis showed that gross inland energy consumption had the highest sensitivity to GHG emissions.
Keywords:
General Regression Neural Network / GHG emission forecasting / Principal component analysis / Principal component regressionSource:
International Journal of Greenhouse Gas Control, 2014, 20, 244-253Publisher:
- Elsevier Sci Ltd, Oxford
Funding / projects:
DOI: 10.1016/j.ijggc.2013.11.011
ISSN: 1750-5836
WoS: 000332264400020
Scopus: 2-s2.0-84889639492
Institution/Community
Tehnološko-metalurški fakultetTY - JOUR AU - Antanasijević, Davor AU - Ristić, Mirjana AU - Perić-Grujić, Aleksandra AU - Pocajt, Viktor PY - 2014 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/2772 AB - The prediction of GHG emissions is very important due to their negative impacts on climate and global warming. The aim of this study was to develop a model for GHG forecasting emissions at the national level using a new approach based on artificial neural networks (ANN) and broadly available sustainability, economical and industrial indicators acting as inputs. The ANN model architecture and training parameters were optimized, with inputs being selected using correlation analysis and principal component analysis. The developed ANN models were compared with the corresponding multiple linear regression (MLR) model, while an ANN model created using transformed inputs (principal components) was compared with a principal component regression (PCR) model. Since the best results were obtained with the ANN model based on correlation analysis, that particular model was selected for the actual 2011 GHG emissions forecasting. The relative errors of the 2010 GHG emissions predictions were used to adjust the ANN model predictions for 2011, which subsequently resulted in the adjusted 2011 predictions having a MAPE value of only 3.60%. Sensitivity analysis showed that gross inland energy consumption had the highest sensitivity to GHG emissions. PB - Elsevier Sci Ltd, Oxford T2 - International Journal of Greenhouse Gas Control T1 - Forecasting GHG emissions using an optimized artificial neural network model based on correlation and principal component analysis EP - 253 SP - 244 VL - 20 DO - 10.1016/j.ijggc.2013.11.011 ER -
@article{ author = "Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor", year = "2014", abstract = "The prediction of GHG emissions is very important due to their negative impacts on climate and global warming. The aim of this study was to develop a model for GHG forecasting emissions at the national level using a new approach based on artificial neural networks (ANN) and broadly available sustainability, economical and industrial indicators acting as inputs. The ANN model architecture and training parameters were optimized, with inputs being selected using correlation analysis and principal component analysis. The developed ANN models were compared with the corresponding multiple linear regression (MLR) model, while an ANN model created using transformed inputs (principal components) was compared with a principal component regression (PCR) model. Since the best results were obtained with the ANN model based on correlation analysis, that particular model was selected for the actual 2011 GHG emissions forecasting. The relative errors of the 2010 GHG emissions predictions were used to adjust the ANN model predictions for 2011, which subsequently resulted in the adjusted 2011 predictions having a MAPE value of only 3.60%. Sensitivity analysis showed that gross inland energy consumption had the highest sensitivity to GHG emissions.", publisher = "Elsevier Sci Ltd, Oxford", journal = "International Journal of Greenhouse Gas Control", title = "Forecasting GHG emissions using an optimized artificial neural network model based on correlation and principal component analysis", pages = "253-244", volume = "20", doi = "10.1016/j.ijggc.2013.11.011" }
Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2014). Forecasting GHG emissions using an optimized artificial neural network model based on correlation and principal component analysis. in International Journal of Greenhouse Gas Control Elsevier Sci Ltd, Oxford., 20, 244-253. https://doi.org/10.1016/j.ijggc.2013.11.011
Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Forecasting GHG emissions using an optimized artificial neural network model based on correlation and principal component analysis. in International Journal of Greenhouse Gas Control. 2014;20:244-253. doi:10.1016/j.ijggc.2013.11.011 .
Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Forecasting GHG emissions using an optimized artificial neural network model based on correlation and principal component analysis" in International Journal of Greenhouse Gas Control, 20 (2014):244-253, https://doi.org/10.1016/j.ijggc.2013.11.011 . .