دانشگاه تبریز دانش آب و خاک 2008-5133 26 شماره 2 بخش 2 2016 08 22 Comparing Regression and Artificial Intelligence Models for Estimating Soil Exchangeable Sodium Percentage from Sodium Absorption Ratio (Case Study: Miankangi Region Soils, Sistan) مقایسه مدل های رگرسیونی و هوش محاسباتی در تخمین درصد سدیم تبادلی از نسبت جذب سدیم (مطالعه موردی: خاکهای منطقه میانکنگی سیستان) 125 137 5385 FA فریدون سارانی دانشجوی سابق کارشناسی ارشد، گروه مهندسی علوم خاک، دانشکده آب و خاک، دانشگاه زابل احمد غلامعلی زاده دانشیار گروه مهندسی علوم خاک، دانشکده آب و خاک، دانشگاه زابل اسما شبانی مربی گروه مهندسی علوم خاک، دانشکده آب و خاک، دانشگاه زابل Journal Article 2016 10 23 Sodium absorption ratio (SAR) and exchangeable sodium percentage (ESP) are two indicators of sodic soils. Several<br />approximate correlations between ESP and SAR for soils of different regions in the world have been reported. The<br />purpose of this study is to find the relationship between ESP and SAR in Miankangi region, in Sistan plain, and<br />assessing possibility of ESP calculation from SAR. Thus, 189 soil samples from the study area were collected and<br />analyzed. Relationship between ESP and SAR was determined by using the logarithmic regression equation of ESP =<br />8.07 × ln(SAR1:1) + 10.20 and linear equation of ESP = 0.78 SAR1:1+ 15.69 (SAR1:1 is SAR in 1:1 soil to water<br />extract), which could explained 83% and 67% of ESP variations respectively. Then, performances of multi-layer<br />perceptron (MLP) network and artificial neuro-fuzzy inference system (ANFIS) were studied. Results showed the<br />capability and better outcomes of MLP and ANFIS in comparison to regression models (correlation coefficient and root<br />mean square error values were 0.94 and 0.05, respectively). These results demonstrated the superiority of intelligent<br />models in explanation of the relationship between ESP and SAR compared with linear and nonlinear regression<br />relations. https://water-soil.tabrizu.ac.ir/article_5385_598dd2a0f5e1a6b47486c6101371648b.pdf