Leila Gholami

Groundwater salinization near salt domes is a major threat to water resources in arid and semi-arid plains, causing a persistent decline in water quality worldwide. Machine learning offers an effective approach for evaluating this risk. This study tested three algorithms—Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (RF)—to estimate groundwater salinity, focusing on the combined roles of land use and climate. The Darab Plain (Iran), where eight salt domes influence groundwater quality, was selected as the study area, and the spatial distribution of the sodium adsorption ratio (SAR) and electrical conductivity (EC) in its groundwater was estimated for 2003, 2013, and 2022, together with their controlling factors. The results showed that the Random Forest model (with an R² value in 2003 of 0.76 for EC and 0.62 for SAR) achieved the highest accuracy and was selected as the best-performing model. Salinity zoning revealed that the eight salt domes exert a strong direct effect on the salinity of adjacent aquifers and an indirect effect on more distant aquifers along groundwater flow paths. Among the 29 variables examined, dependence-plot analysis of the trained models showed that two collinear terrain-elevation proxies, land surface temperature and channel network base level, most strongly explained both EC and SAR in nearly every modeled year, with temperature and precipitation also consistently influential where climatic data were available. Given the projected warming trend in the region, local authorities and stakeholders should prioritize improved irrigation practices before considering water-management strategies that anticipate reduced agricultural productivity and associated population migration.

Straw mulch cover is one of the most important soil erosion control measures applied to reduce runoff and soil loss in cultivated areas. However, in developing countries such as Iran, without a clear tradition or knowledge about soil erosion control measures, the use of straw mulch is rare, and its impact in the most extended crops is not well understood. We investigated the separate and combined effects of colza (Brassica napus L.) and corn (Zea mays L.), to mitigate the activation of soil loss and runoff in sandy-loam soils, under different antecedent soil moisture conditions, in a rainfed plot in Northern Iran. Under laboratory conditions, we used a rainfall simulator device. The experiments were performed by using a rainfall intensity of 50 mm h⁻¹, with a duration of 10 min and an inclination of 30%, with three replications. These conditions were used to evaluate the soils under extreme meteorological and topographical conditions. Two types of straw mulch, colza and corn, separated and combined with three different cover levels (25, 50 and 75%) and four distinct antecedent soil moisture conditions (0, 15, 20 and 30%), were used. The results showed that the applied straw mulches had significant effects on the reduction of soil loss and sediment concentration, by almost 99%. The maximum reduction of soil loss and sediment concentration was observed for the treatments with 0% moisture and 75% of corn, colza + corn and colza, with a reduction of 93.8, 92.2 and 84.9% for soil loss, respectively, and 91.1, 85.7 and, 60.7% for sediment concentration, respectively. The maximum reduction of runoff was also obtained with 0% soil moisture and a cover of 75%, reducing 62.5, 48.5 and 34.8% for colza, colza + corn and corn, respectively. The corn straw mulch showed the highest effectivity on reducing soil loss and sediment concentration toward colza treatment. But the colza straw mulch showed the best results on reducing runoff toward corn treatment. We conclude that the application of straw mulch is affordable and useful in reducing soil loss and runoff, instead of bare soils.