Author/Authors :
-، - نويسنده Department of Agricultural Machinery Engineering, Faculty of Agricultural
Engineering and Technology, University of Tehran, Karaj, Iran Khoshnevisan, B , -، - نويسنده Department of Agricultural Machinery Engineering, Faculty of Agricultural
Engineering and Technology, University of Tehran, Karaj, Iran Rafiee, Sh. , -، - نويسنده cDepartment of Software Engineering, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia Iqbald, J. , -، - نويسنده Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia. Shamshirbande, Sh. , -، - نويسنده Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, University of Tehran, Karaj, Islamic Republic of Iran. Omid, M. , -، - نويسنده Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia Anuarf, N. B. , -، - نويسنده Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia Abdul Wahabg, A. W.
Abstract :
In this study greenhouse tomato production was investigated from energy consumption and greenhouse gas (GHG) emission point of views. Moreover, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS) were employed to model energy consumption for greenhouse tomato production. Total energy input and output were calculated as 1316.14 and 281.1 GJ/ha. Among the all energy inputs natural gas and electricity had the most significant contribution to the total energy input. Evaluations of GHG emission illustrated that the total GHG emission was estimated at 34758.11 kg CO2eq./ha and among all inputs, electricity played the most important role, followed by natural gas. Drawing a comparison between ANN and ANFIS models demonstrated that the ANFIS-based models due to employing fuzzy rules can model output energy more accurate than ANN models. Accordingly, Correlation coefficient (R), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) for the best ANFIS architecture were calculated as 0.983, 0.025 and 0.149, respectively while these performance parameters for the best ANN model was computed as 0.933, 0.05414 and 0.279, respectively.
