A proposed artificial neural network approach to Predict wheat production: The case of Iran country
Mahsa Rouzbahman, Rana Jalali and Reza ghodsi
The 2010 Summer Computer Simulation Conference (SCSC 10)
Ottawa, Canada, July 11-14, 2010
An analysis of the effects of various factors such as climate factors on wheat yield was performed in Iran country in order to obtain models suitable for yield estimation and regional grain production prediction. Climate data from meteorological records and other data from central bank of Iran were employed. Annual data for 18 years were applied in this study. In order to predict wheat production, artificial neural networks (ANN) methodologies were tested for analyzing the data. To conduct this review, we have considered 8 factors as inputs and wheat production is used as output for the ANN algorithm. Our input variables are: rainfall, guaranteed purchasing price, area under cultivation, subsidy, insured area, inventory, import, population, value-added of agriculture group. The comparison of real wheat production with ANN output in the last five years of this study shows that the proposed ANN model is a suitable way of predicting wheat production.
Conference Manager (V2.56.8 - Rev. 1182)