Ashkan Nabavi-Pelesaraei - Department of Agricultural Machinery Engineering, Faculty of Agriculture, University of Tabriz, Iran.
Sajjad Shaker-Koohi - Department of Agronomy and Plant Breeding, Faculty of Agriculture, University of Tabriz, Iran.
Mohammad Bagher Dehpour - Department of Agricultural Mechanization Engineering, Faculty of Agriculture, University of Guilan,Iran.

This paper studies the modeling and optimization of energy use and greenhouse gas emissions of eggplant production using artificial neural network and multi-objective genetic algorithm in Guilan province of Iran. Results showed that the highest share of energy consumption belongs to diesel fuel (49.24%); followed by nitrogen (33.30%). The results indicated that a total energy input of 13910.67 MJ ha-1 was consumed for eggplant production. In ANN, the Levenberg-Marquardt Algorithm was examined to finding best topology for modeling and optimization of energy inputs an GHG emissions for eggplantproduction. The results of ANN indicated the best topology with 12-9-9-2 structure had the highest R2, lowest RMSE and MAPE. Also, the multi-objective optimization was done by MOGA. In this research, 42 optimal was introduced by MOGA based minimum total GHG emissions and maximum yield of eggplant production, in the studied area. Also, the results revealed that the best generation with lowestenergy use was consumed about 4597 MJ per hectare. The GHG emissions of best generation was calculated as about 127 kg CO2eq. ha-1. The potential of GHG reduction by MOGA was computed as 388.48 kg CO2eq. ha-1. Also, the highest reduction of GHG emissions belongs to diesel fuel with 65.05%.

Eggplant; Energy consumption; Greenhouse gas emissions; Modeling; Optimization