Estimating Saturated Hydraulic Conductivity Using Decision Tree Analysis.

Pedotransfer functions (PTFs) are useful tools that can help predict saturated hydraulic conductivity (Ksat). However, at present, most PTFs only utilize soil texture and bulk density. There are numerous other properties, including soil structure, which are available in soil survey databases and may be useful for more accurately predicting Ksat_.  In our study we want to determine which of these, if any, will give a more accurate prediction of Ksat.  We have used soil profile descriptions from the S-124 regional project dataset.  This is a Southern Cooperative Bulletin Series which contains 21 soil series descriptions from all over the Southeastern United States. These bulletins contain qualitative soil structure descriptions that we used to determine the most important properties in the prediction of Ksat.  We have broken down the descriptors into six qualitative and two quantitative groups: horizon position (TOP), textural class (TXT), ped size (PED), crack orientation (CRK), bulk density and organic matter (BDO), grade (GRD), moist consistence (CST), and particle size distribution (PSD).  Qualitative type variables were represented by zeros and ones, determined by the samples’ membership in the respective groups. Results indicate that structure is an important variable in the prediction of Ksat.  Using the decision-tree model developed by Lilly et al. (2008), we were able to predict Ksat with a RMSR  less than a log₁₀ transformed order of magnitude.