تعیین ترکیب بهینه متغیرهای ورودی با استفاده از آزمون گاما برای مدل‌سازی پتاسیم قابل جذب در سیستم عصبی-فازی (مطالعه موردی: منطقه میانکنگی؛ زابل)

One of the important and complex steps for nonlinear modeling is pre-processing of input data in order to select the appropriate combination of them in the model. The gamma test was used to select the optimal combination of input variables for available potassium modeling in this study. The M test was used for determining the optimal number of data needed for modeling. Eight input variables were used for modeling. Modeling the available potassium was done by the number of optimum points and selected variables with subtractive clustering in the fuzzy neural system. The results showed that six variables (clay percentage, silt, organic matter, electrical conductivity, saturation moisture and pH) are the optimal combination of variables in modeling the available potassium in Mian-Kangi region. Also, 112 of measured data (60%) were considered as suitable data for the modeling training section using the M test results. The results indicated that the M method has better accuracy and speed than the trial and error method for finding the appropriate number of input data in training section. The results of modeling also indicated that the fuzzy neural method has high capability and performance in estimating the amount of available potassium in the soil of Mian-Kangi region (R2 = 0.90 and RMSE = 4.27). Also, organic carbon percentage was the most important input for modeling and predicting the amount of available potassium.

کلیدواژه ها:

آزمون M ، آزمون گاما ، پتاسیم قابل جذب ، عصبی فازی ، ویژگی‌های زودیافت