Modeling of methane emissions using the artificial neural network approach

Abstract

The aim of this study was to develop a model for forecasting CH4 emissions at the national level, using artificial neural networks (ANN) with broadly available sustainability, economical and industrial indicators as their inputs. ANN modeling was performed using two different types of architecture; a backpropagation neural network (BPNN) and a general regression neural network (GRNN). A conventional multiple linear regression (MLR) model was also developed in order to compare the model performance and assess which model provides the best results. ANN and MLR models were developed and tested using the same annual data for 20 European countries. The ANN model demonstrated very good performance, significantly better than the MLR model. It was shown that a forecast of CH4 emissions at the national level using the ANN model could be made successfully and accurately for a future period of up to two years, thereby opening the possibility to apply such a modeling technique, which could be used to support the implementation of sustainable development strategies and environmental management policies.