No abstract

Groundwater quality assessment is vital to protect this resource. Therefore, the aims of this study were to evaluate the hydro-chemical quality of the Marvdasht aquifer located in the semi-arid region of Iran and to map the groundwater quality parameters. For this purpose, a mean data of 11 groundwater quality parameters collected from 49 wells (2010–2015) were used. Pie, Schoeller and Piper diagrams were used to determine the dominant ions and type of water. Ion ratios and Gibbs diagrams were used to illustrate the chemistry and processes in the groundwater. Spatial distribution of quality parameters were mapped using ArcGIS. Results showed that the water type is Na-Cl and Cl− with abundance orders of CL− > SO42− > HCO3− and Na+ with abundance orders of Na+ > Mg2 + >Ca2+ > K+ are dominant anion and cation, respectively. Gibbs diagrams revealed that geological formations control the groundwater chemistry in 66% of the groundwater samples. Based on the Wilcox diagram, only 24% of the samples fell into the C4–S4 class with high salinity and alkalinity hazard. The maps showed that generally groundwater in the north of the study site has better quality than that the south of the study site, where the existence of dolomite and chalky formations leads to decreasing water quality.

Due to the physical processes of floods, the use of data-driven machine learning (ML) models is a cost-efficient approach to flood modeling. The innovation of the current study revolves around the development of tree-based ML models, including Rotation Forest (ROF), Alternating Decision Tree (ADTree), and Random Forest (RF) via binary particle swarm optimization (BPSO), to estimate flood susceptibility in the Maneh and Samalqan watershed, Iran. Therefore, to implement the models, 370 flood-prone locations in the case study were identified (2016–2019). In addition, 20 hydrogeological, topographical, geological, and environmental criteria affecting flood occurrence in the study area were extracted to predict flood susceptibility. The area under the curve (AUC) and a variety of other statistical indicators were used to evaluate the performances of the models. The results showed that the RF-BPSO (AUC=0.935) has the highest accuracy compared to ROF-BPSO (AUC=0.904), and ADTree-BPSO (AUC=0.923). In addition, the findings illustrated that the chance of flooding in the center of the area in question is greater than in other points due to lower elevation, lower slope, and proximity to rivers. Therefore, the ensemble framework proposed here can also be used to predict flood susceptibility maps in other regions with similar geo-environmental characteristics for flood management and prevention.