Gully erosion destroys agricultural and domestic grazing land in many countries, especially those with arid and semi-arid climates and easily eroded rocks and soils. It also generates large amounts of sediment that can adversely impact downstream river channels. The main objective of this research is to accurately detect and predict areas prone to gully erosion. In this paper, we couple hybrid models of a commonly used base classifier (reduced pruning error tree, REPTree) with AdaBoost (AB), bagging (Bag), and random subspace (RS) algorithms to create gully erosion susceptibility maps for a sub-basin of the Shoor River watershed in northwestern Iran. We compare the performance of these models in terms of their ability to predict gully erosion and discuss their potential use in other arid and semi-arid areas. Our database comprises 242 gully erosion locations, which we randomly divided into training and testing sets with a ratio of 70/30. Based on expert knowledge and analysis of aerial photographs and satellite images, we selected 12 conditioning factors for gully erosion. We used multi-collinearity statistical techniques in the modeling process, and checked model performance using statistical indexes including precision, recall, F-measure, Matthew correlation coefficient (MCC), receiver operatic characteristic curve (ROC), precision–recall graph (PRC), Kappa, root mean square error (RMSE), relative absolute error (PRSE), mean absolute error (MAE), and relative absolute error (RAE). Results show that rainfall, elevation, and river density are the most important factors for gully erosion susceptibility mapping in the study area. All three hybrid models that we tested significantly enhanced and improved the predictive power of REPTree (AUC=0.800), but the RS-REPTree (AUC= 0.860) ensemble model outperformed the Bag-REPTree (AUC= 0.841) and the AB-REPTree (AUC= 0.805) models. We suggest that decision makers, planners, and environmental engineers employ the RS-REPTree hybrid model to better manage gully erosion-prone areas in Iran.

Due to numerous droughts in recent years, the amount of surface water in arid and semi-arid regions has decreased significantly, so reliance on groundwater to meet local and regional demands has increased. The Kabgian watershed is a karst watershed in southwestern Iran that provides a significant proportion of drinking and agriculture water supplies in the area. This study identified areas with karst groundwater potential using a combination of machine learning and statistical models, including entropy-SVM-LN, entropy-SVM-SG, and entropy-SVM-RBF. To do this, 384 karst springs were identified and mapped. Sixteen factors that are related to karst potential were identified from a review of the literature, and these were compiled for the study area. The 384 locations were randomly separated into two categories for training (269 location) and validation (115 location) datasets to be used in the modeling process. The ROC curve was used to evaluate the modeling results. The models used, in general, were good at determining the location of karst groundwater potential. The evaluation showed that the E-SVM-RBF model had an area under the curve of 0.92, indicating that it was most accurate estimator of groundwater potential among the ensemble models. Evaluation of the relative importance of each of the 16 factors revealed that land use, a vector ruggedness measure, curvature, and topography roughness index were the most important explainers of the presence of karst groundwater in the study area. It was also found that the factors affecting the presence of karst springs are significantly different from non-karst springs.

The health of drinking water is an important criterion for developed countries and around half of the world’s population is deprived of sanitary and safe drinking water. By identifying the time of pollution occurrence and the places that are most sensitive to pollution the management of the quality of drinking water can be planned. Since the landfill for Yasouj, a city in Iran, was located in a higher place than the drinking water wells, which were drilled in a karst aquifer, the safety of the drinking water resources (including eight wells) of Yasouj were investigated in the present study. For this purpose, different parameters, comprising the concentration of eight heavy metals and eight ions, alkalinity, total harness, pH, biological oxygen demand (BOD5) and total coliform, were measured over 12 months and the obtained data were compared with the WHO’s and Iran’s drinking water standards. To assess the measured data statistically, SPSS software was applied. From the reported results, the water characterizations of the wells complied with the mentioned standards; however, four of the wells were more prone to supply higher quality water. It is noted that Hg, Cd, and the total coliform of wells were close to the permissible values reported by both the aforementioned standards. Therefore, the water obtained from wells should be disinfected before using and Hg and Cd concentrations need to be monitored regularly to prevent poisoning. Due to the rapid movement of pollutants in karst areas, it is very important to detect their presence in the water resources over time. Consequently, continuous monitoring and sampling is one of the most important protection dealings for karst aquifers.

Nutrient input through submarine groundwater discharge (SGD) often plays a significant role in primary productivity and nutrient cycling in the coastal areas. Understanding relationships between SGD and topo-hydrological and geo-environmental characteristics of upstream zones is essential for sustainable development in these areas. However, these important relationships have not yet been completely explored using data-mining approaches, especially in arid and semi-arid coastal lands. Here, Landsat 8 thermal sensor data were used to identify potential sites of SGD at a regional scale. Relationships between the remotely-sensed sea surface temperature (SST) patterns and geo-environmental variables of upland watersheds were analyzed using logistic regression model for the first time. The accuracy of the predictions was evaluated using the area under the receiver operating characteristic curve (AUC-ROC) metric. A highly accurate model, with the AUC-ROC of 96.6%, was generated. Moreover, the results indicated that the percentage of karstic lithological formation and topographic wetness index were key variables influencing SGD phenomenon and spatial distribution in the northern coastal areas of the Persian Gulf. The adopted methodology and applied metrics can be transferred to other coastal regions as a rapid assessment procedure for SGD site detection. Moreover, the results can help planners and decision-makers to develop efficient environmental management strategies and the design of comprehensive sustainable development policies.