Author/Authors :
Khoshnevisan، B نويسنده M.Sc. Student, Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, University of Tehran, Karaj, Iran , , Rafiee، S نويسنده Professor, Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, University of Tehr , , omid، m نويسنده Professor, Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, University of Tehran, Karaj, Iran. , , Mousazadeh، H نويسنده Associate Professor, Department of Agricultural Machinery Engineering, Faculty of Agricultural Engineering and Technology, University of ,
Abstract :
In this study an artificial neural network was developed to predict output the energy and GHG emission of open field (OF) and greenhouse (G) strawberry production system. Data were randomly collected from OFs and Gs in Guilan province of Iran. For both systems the best models included an input layer, two hidden layers with hyperbolic tangent algorithm and an output layer with linear hyperbolic tangent algorithm. The structures of 11-6-10-2 and 13-7-6-2 were selected as the best topologies for OF and G production systems, respectively. These topologies had the least root mean square errors (RMSE) and mean absolute errors (MAE).
