International Academic Journal of Politics and Law

  • ISSN 0000-0000

Use of the Intelligent Models to Predict the Rice Potential Production

Nafiseh Yaghmaeian Mahabadi

Abstract: Agricultural system is very complex since it deals with large data situation which comes from a number of factors. A lot of techniques and approaches have been used to identify any interactions between factors that affecting yields with the crop performances. The application of neural network to the task of solving non-linear and complex systems is promising. The objectives of the present study were to investigate whether artificial neural network (ANN) models could effectively predict rice potential in Astane region, Northern Iran. In this research, potential production was calculated using AEZ model. Mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R2) criterions were used to evaluate the performance of the ANN. ANN rice grain yield models resulted in R2, RMSE and RMSE of 0.87, 0.36 and 0.41. These results show high performance trained neural network to predict the yield of rice. Sensitivity analysis showed that rice potential production has the most dependency to soil pH, electrical conductivity and percentage of organic matters. Application of neural network can improve the prediction of rice yield in the study region

Keywords: Artificial neural networks, Crop yield prediction, Rice, Northern Iran

Page: 14-25

DOI: 10.9756/IAJPL/V5I1/1810007

Volume 5, Issue 2, 2018