Soil erosion is a serious threat to sustainable agriculture, food production, and environmental security. The advancement of accurate models for soil erosion susceptibility and hazard assessment is of utmost importance for enhancing mitigation policies and laws. This paper proposes novel machine learning (ML) models for the susceptibility mapping of the water erosion of soil. The weighted subspace random forest (WSRF), Gaussian process with a radial basis function kernel (Gaussprradial), and naive Bayes (NB) ML methods were used in the prediction of the soil erosion susceptibility. Data included 227 samples of erosion and non-erosion locations through field surveys to advance models of the spatial distribution using predictive factors. In this study, 19 effective factors of soil erosion were considered. The critical factors were selected using simulated annealing feature selection (SAFS). The critical factors included aspect, curvature, slope length, flow accumulation, rainfall erosivity factor, distance from the stream, drainage density, fault density, normalized difference vegetation index (NDVI), hydrologic soil group, soil texture, and lithology. The dataset cells of samples (70% for training and 30% for testing) were randomly prepared to assess the robustness of the different models. The functional relevance between soil erosion and effective factors was computed using the ML models. The ML models were evaluated using different metrics, including accuracy, the kappa coefficient, and the probability of detection (POD). The accuracies of the WSRF, Gaussprradial, and NB methods were 0.91, 0.88, and 0.85, respectively, for the testing data; 0.82, 0.76, and 0.71, respectively, for the kappa coefficient; and 0.94, 0.94, and 0.94, respectively, for POD. However, the ML models, especially the WSRF, had an acceptable performance regarding producing soil erosion susceptibility maps. Maps produced with the most robust models can be a useful tool for sustainable management, watershed conservation, and the reduction of soil and water loss.

The mountainous watersheds are increasingly challenged with extreme erosions and devastating floods due to climate change and human interventions. Hazard mapping is essential for local policymaking for prevention, planning the mitigation actions, and also adaptation to extremes. This study proposes novel predictive models for susceptibility mapping for flood and erosion. Furthermore, this study elaborates on prioritizing the existing sub-basins in terms of erosion and flood susceptibility. A comparative analysis of generalized linear model (GLM), flexible discriminate analyses (FDA), multivariate adaptive regression spline (MARS), random forest (RF), and their ensemble is performed to ensure highest predictive performance. Furthermore, the priority of the sub-basins in terms of sensitivity to erosion and flood was determined based on the best model. The results showed that the GLM, FDA, MARS, RF, and ensemble models had an area under curve (AUC) 0.91, 0.92, 0.89, 0.93 and 0.94, respectively, in modeling the flood susceptibility. Also, the GLM, FDA, MARS, RF, and ensemble models had an AUC of 0.93, 0.92, 0.89, 0.96, and 0.97, respectively, in determining erosion susceptibility. Priority assessment based on the best model, the ensemble approach, indicated that the sub-basins SW3 and SW5 were found to have high sensitivity to the flood and soil erosion, respectively.

Groundwater resources, unlike surface water, are more vulnerable to disturbances and contaminations, as they take a very long time and significant cost to recover. So, predictive modeling and prevention strategies can empower policymakers for efficient groundwater governance through informed decisions and recommendations. Due to the importance of groundwater quality modeling, the hardness susceptibility mapping using machine learning (ML) models has not been explored. For the first time, the current research aimed to predict groundwater hardness susceptibility using the ML models. The performance of two ensemble models of boosted regression trees (BRT) and random forest (RF) is investigated through the arrangement of a comparative study with multivariate discriminant analysis (MDA). According to the hardness values in 135 groundwater quality monitoring wells, the hard and soft water are determined; then, 11 predictor variables including distance from the sea (DFS), land use, elevation, distance from the river (DFR), depth to groundwater (DTGW), pH, precipitation (PCP), evaporation (E), groundwater level (GWL), curvature, and lithology are used for predicting the groundwater hardness susceptibility map. Results indicated that the variables of DFR, DTGW, elevation, and DFS had a higher contribution to the modeling process. So, the high harness areas are mostly related to low elevations, low DTGW, and proximity to river and sea, which facilitate the percolation conditions for minerals containing calcium or magnesium into groundwater.

Risk and susceptibility mapping of groundwater salinity (GWS) are challenging tasks for groundwater quality monitoring and management. Advancement of accurate prediction systems is essential for the identification of vulnerable areas in order to raise awareness about the potential salinity susceptibility and protect the groundwater and top-soil in due time. In this study, three machine learning models of Stochastic Gradient Boosting (StoGB), Rotation Forest (RotFor), and Bayesian Generalized Linear Model (Bayesglm) are developed for building prediction models and their performance evaluated in the delineation of salinity susceptibility maps. Both natural and human effective factors (16 features) were used as predictors for groundwater salinity modeling and were randomly divided into the training (80%) and testing (20%) datasets. The models were evaluated using testing datasets after calibration using the selected features by recursive feature elimination (RFE) method. The RFE indicated that modeling with 8 features had better performance among 1 to 16 features (Accuracy = 0.87). Results of the groundwater salinity prediction highlighted that StoGB had a good performance, whereas the RotFor and Bayesglm had an excellent performance based on the Kappa values (> 0.85). Although spatial prediction of the models was different, all of the models indicated that central parts of the region have a very high susceptibility which matches with agricultural areas, lithology map, the locations with low depth to groundwater, low slope, and elevation. Additionally, areas near to the Maharlu lake and locations with a high decline in groundwater are also located in the very high susceptibility zone, which can confirm the effects of saltwater intrusion. The susceptibility maps produced in this study are of utmost importance for water security and sustainable agriculture.