Modeling of energy consumption and GHG (greenhouse gas) emissions in wheat production in Esfahan province of Iran using artificial neural networks

This study was carried out in Esfahan province of Iran. Data were collected from 260 farms in Fereydonshahr city with face to face questionnaire method. The objective of this study was to predict wheat production yield and (greenhouse gas) GHG emissions on the basis of energy inputs. Accordingly, several (artificial neural network) ANN models were developed and the prediction accuracy of them was evaluated using the quality parameters. The results illustrated that average total input and output energy of wheat production were 80.1 and 38 GJ ha−1, respectively. Electricity, chemical fertilizers and water for irrigation were the most influential factors in energy consumption with amount of 39.5, 23.3 and 6.17 GJ ha−1, respectively. Energy use efficiency and energy productivity were 0.032 GJ kg−1 and 34.1 kg GJ−1, respectively. The ANN model with 11-3-2 structure was the best one for predicting the wheat yield and GHG emissions. The coefficients of determination (R2) of the best topology were 0.99 and 0.998 for wheat yield and GHG emissions, respectively.