JWSS - Journal of Water and Soil Science

The present research was conducted to determine water stress tolerance and water productivity (WP) of 5 alfalfa cultivars as a split-plot design in a randomized complete block with 3 replications in the Safiabad Agriculture and Natural Resources Research Center (SARRC) with Silty clay loam soil texture during 2018-2019. The main plot was 4 levels of water irrigation depth (including 25, 50, 75, and 100% water requirement supply) with a constant irrigation cycle and the sub-plot was the five alfalfa cultivars (Baghdadi, Yazdi, Nikshahree, Omid, and Mesasirsa). Two-year data on forage yield and WP for six harvests (from June to November) were analyzed by SAS software. The results showed that the wet and dry forage yield decreased by applying water stress and the percentage of dry forage increased. The highest yield of dry matter (12.4 tons ha^-1) and WP of dry forage (0.94 kg m^-3) were obtained from 75% water requirement supply treatment. Baghdadi genotype with wet and dry forage yield 39.1 and 10.7 tons ha^-1, respectively, and the WP of dry forage 0.9 kg m^-3 was higher than other genotypes. However, the Yazdi genotype had the lowest yield of wet and dry forage (30.3 and 8.5 tons ha^-1, respectively) and dry forage WP (0.75 kg m^-3). Therefore, the Baghdadi genotype with a 75% water requirement supply is recommended for similar conditions to the climate of Northern Khuzestan to increase water productivity.

An accurate and reliable prediction of groundwater level in a region is very important for sustainable use and management of water resources. In this study, the generalized feedforward (GFF) and radial basis function (RBF) of artificial neural networks (ANNs) have been evaluated for monthly predicting groundwater levels in the Dezful-Andimeshk plain in southwestern Iran. The partial mutual information (PMI) algorithm was used to determine efficient input variables in ANNs. The results of using the PMI algorithm showed that efficient input variables for monthly predicting groundwater level for piezometers affected by water discharge and recharge include only water level in the current month. Also, efficient input variables for predicting the water level for piezometers affected only by water discharge include the water level in the current month, the water level in the previous month, the water level in the previous two months, transverse coordinates of piezometers to UTM, the water level in the previous three months, the water level in the previous four months, the water level in the previous five months and longitudinal coordinates of piezometers to UTM. In addition, efficient input variables of monthly predicting groundwater level for piezometers neither affected by water discharge nor water recharge, respectively, include the water level in the current month, the water level in the previous month, the water level in the previous two months, the water level in the previous three months, the water level in the previous four months, the water level in the previous five months, the water level in the previous six months, transverse coordinates of piezometer to UTM and longitudinal coordinates of piezometer to UTM. The results indicated that the GFF network is more accurate than the RBF network for monthly predicting groundwater level for piezometers including water discharge and recharge and piezometers including only water discharge. Also, the RBF network is more accurate for monthly predicting groundwater levels for piezometers that include neither water discharge nor recharge than the GFF network.