www.pelagiaresearchlibrary.com t Available online a Pelagia Research Library European Journal of Experimental Biology, 2014, 4(3):240-245 ISSN: 2248 –9215 CODEN (USA): EJEBAU 240 Pelagia Research Library Surveying on energy pattern and application of neural network for predict energy consumption for wheat production in Iran Mohamad Reza Moghimi 1* , Mohsen Pooya², Behzad Mohammadi Alasti³ and Mehdi Abasgholipor Ghadim³ 1 Young Researchers Club, Ghorveh Branch, Islamic Azad University, Ghorveh, Iran 2 Department of Mechanization Engineering, University of Tehran, Science and Research, Khozestan, Iran 3 Department of Agricultural Machinery, Bonab Branch, Islamic Azad University Bonab, Iran _____________________________________________________________________________________________ ABSTRACT The aim of this study was to examine energy use pattern and predict the output energy for dry wheat production in Gorve country, Kordestan province of Iran. The data used in this study were collected from farmers by using a face to face survey. The results revealed that wheat production consumed a total of 42.998 G J ha –1 and output was 97.935 G J ha –1 . Electricity has the highest share by 26.135 G J ha –1 followed by total fertilizers and diesel fuel. In this study, several direct and indirect factors have been identified to create an artificial neural networks (ANN) model to predict output energy for wheat production. The final model can predict output energy based on human labor, machinery, diesel fuel, chemical fertilizer, biocides, electricity and seed. The results of ANNs analyze showed that the (7-6-6-1)-MLP, namely, a network having six neurons in the first and second hidden layer was the best- suited model estimating the output energy. For this topology, MSE and R 2 were 0.003 and 94%, respectively. The sensitivity analysis of input parameters on output showed that total chemical fertilizer and seed had the highest and lowest sensitivity on output energy with 22% and 7%, respectively. Key words: Artificial neural networks, Energy consumption, wheat production, Iran _____________________________________________________________________________________________ INTRODUCTION Agriculture is both a producer and consumer of energy. It uses large quantities of locally available non-commercial energy, such as seed, manure and animate energy, as well as commercial energies, directly and indirectly, in the form of diesel, electricity, fertilizer, plant protection, chemicals, irrigation water, machinery etc. [11]. Efficient use of energy in agriculture is one of the principal requirements for sustainable agricultural production. Improving energy use efficiency is becoming increasingly important for combating rising energy costs, depletion of natural resources and environmental deterioration [6]. The development of energy efficient agricultural systems with low input energy compared to the output of food can reduce the greenhouse gas emissions from agricultural production systems [5]. The energy input–output analysis is usually made to determine the energy efficiency and environmental aspects. This analysis will determine how efficient the energy is used. Sensitivity analysis quantifies the sensitivity of a model's state variables to the parameters defining the model. It refers to changes in the response of each of the state variables which result from small changes in the parameter values. Sensitivity analysis is valuable because it identifies those parameters which have most influence on the response of the model. It is also an essential prerequisite to any parameter optimization exercise [4, 23]. In recent years, many researchers have investigated the energy use for agricultural crop production. Taki et al [26] studied the energy use patterns of cucumber production in Iran and found that the fertilizer application have the highest energy source in total inputs. Bahrami et al [3] studied the productive efficiency for wheat production in Iran by means of data envelopment analysis (DEA). An