Neural Network Predictions

The HYDRUS code was coupled with the Rosetta Lite DLL (Dynamically Linked Library), which was independently developed by Marcel Schaap at the U.S. Salinity Laboratory [Schaap et al., 2001]. Rosetta implements pedotransfer functions (PTFs) which predict van Genuchten’s [1980] water retention parameters and the saturated hydraulic conductivity (Ks) in a hierarchical manner from soil textural class, the soil textural distribution, bulk density and one or two water retention points as input. Rosetta has its own help features containing all relevant information and references. Rosetta provides soil hydraulic parameters for the analytical functions of van Genuchten [1980] for twelve textural classes of the USDA textural triangle.