Estimation of Daily Yield of Corn Using Fuzzy Inference Systems

In this study the possibility of using fuzzy inference system efficiency, creating a bridge between meteorological, plant parameters, and Daily Yield, and comparing the accuracy of Daily Yield using these systems were investigated. After analyzing the different models and different combinations of daily meteorological data, seven models for estimating daily Yield were presented. For these models, the calculated Yield from AQUACROP model was considered as a base and the efficiency of other models was evluated using statistical methods such as root mean squared error, error of the mean deviation, coefficient of determination, Jacovides (t) and Sabbagh et al. (R2/t) criteria. an experiment was carried out during the 2014-2015 growing season in the Agricultural Research and Education Center of Khorasane Razavi province using a randomized complete block design with a split plot arrangement and four replications. This experiment was including of three irrigation levels treatments as the main plot and three method of planting treatments (transplanting 20-days, transplanting 30-days and direct seeded) as subplots. From the available data,75 percent was used for training the model and the rest of 25 percent was utilized for the testing purposes. The results derived from the fuzzy models with different input parameters as compared with AQUACROP model showed that fuzzy systems were very well able to estimate the daily Yield.Fuzzy model so that the highest correlation with the 9 input variables (r=0.98) had in mind and evaluate other parameters, the model with2 parameters, match very well with the AQUACROP model had stage training. In the test phase,training phase was very similar results and the model with the second phase of harvest index and canopy cover will get the best match. According to the results of this study it can be concluded that fuzzy model approach is an appropriate method to estimate the daily yield .