A macroscopic root extraction model was used with four different reduction functions for salinity stress in the numerical simulation model HYSWASOR. Most of the parameter values originally proposed for these functions did not provide good agreement with the experimental data. Therefore, the parameter values were derived from extensive measurements of one of five salinity treatments of alfalfa experiments in the greenhouse and then validated with the four remaining treatments. The simulation results indicated that a well-known crop yield response function can be used as a water uptake term, using the same crop-specific slope and a modified salinity threshold value. The most sensitive part of this reduction function appeared to be the threshold value; while for the non-linear reduction function, without a threshold, the major sensitivity lies in its shape parameter. The simulated actual cumulative transpirations are rather close to the experimental values, while the simulated soil water contents and soil solution osmotic heads indicate some discrepancies with the actual data, but the mean values of these variables are very close to the measured data. While the non-linear two-threshold reduction function provides better agreement with the experimental data for most treatments, all other functions provided close results. This observation suggests the use of the simple linear reduction function in simulation models. (C) 2002 Elsevier Science B.V. All rights reserved.
