Prediction of unsaturated soil hydraulic conductivity using air permeability: Regression approach

Abstract

A close correlation between water conductivity (<italic>K(θ)</italic>) and air permeability (<italic>K</italic><sub><italic>a</italic></sub>), measured at various water contents, is expected due to tight dependence of water filled porosity to air filled porosity of soils. Finding such a relation will greatly facilitate the prediction of unsaturated water conductivity (<italic>K(θ)</italic>). So, the purpose of the current investigation was to find out if a reliable relation or function between the two permeabilities can be established. In this regard, <italic>K(θ)</italic> and <italic>K</italic><sub><italic>a</italic></sub> were measured by pressure plate outflow and variable head methods, respectively, at the range of 0 to -100 kPa matric potential (<italic>ψ</italic><sub><italic>m</italic></sub>). A linear regression function between relative water conductivity (<italic>K</italic><sub><italic>r</italic></sub>(<italic>θ</italic>)) and <italic>K</italic><sub><italic>a</italic></sub> (<italic>LogK</italic><sub><italic>r</italic></sub> (<italic>θ</italic>)=<italic>a</italic>+<italic>bLogK</italic><sub><italic>a</italic></sub>) with the correlation coefficient (<italic>R</italic>) from 0.884 to 0.999 were established for the 22 examined soils. The overall <italic>R</italic> for 128 data pairs (<italic>K</italic><sub><italic>r</italic></sub>(<italic>θ</italic>) and <italic>K</italic><sub><italic>a</italic></sub>) became 0.821 (being significant at <italic>P</italic><0.01) with the slope (<italic>b</italic>) of -2.54 and intercept (<italic>a</italic>) of -10.93. For the comparison propose <italic>K</italic><sub><italic>r</italic></sub>(<italic>θ</italic>) were also predicted from RETC using experimental SMC data and van Genuchten and Brooks-Corey models. The reliability of the <italic>K</italic><sub><italic>r</italic></sub>(<italic>θ</italic>) prediction from <italic>K</italic><sub><italic>a</italic></sub> based on root mean square error (RMSE), geometric mean error ratio (GMER), and geometric standard deviation of error ratio (GSDER) criteria became considerable greater than those predicted from the two mentioned models.