No abstract

Knowledge of the groundwater potential, especially in an arid region, can play a major role in planning the sustainable management of groundwater resources. In this study, nine machine learning (ML) algorithms—namely, Artificial Neural Network (ANN), Decision Jungle (DJ), Averaged Perceptron (AP), Bayes Point Machine (BPM), Decision Forest (DF), Locally-Deep Support Vector Machine (LD-SVM), Boosted Decision Tree (BDT), Logistic Regression (LG), and Support Vector Machine (SVM)—were run on the Microsoft Azure cloud computing platform to model the groundwater potential. We investigated the relationship between 512 operating boreholes with a specified specific capacity and 14 groundwater-influencing occurrence factors. The unconfined aquifer in the Nineveh plain, Mosul Governorate, northern Iraq, was used as a case study. The groundwater-influencing factors used included elevation, slope, curvature, topographic wetness index, stream power index, soil, land use/land cover (LULC), geology, drainage density, aquifer saturated thickness, aquifer hydraulic conductivity, aquifer specific yield, depth to groundwater, distance to faults, and fault density. Analysis of the contribution of these factors in groundwater potential using information gain ratio indicated that aquifer saturated thickness, rainfall, hydraulic conductivity, depth to groundwater, specific yield, and elevation were the most important factors (average merit > 0.1), followed by geology, fault density, drainage density, soil, LULC, and distance to faults (average merit < 0.1). The average merits for the remaining factors were zero, and thus, these factors were removed from the analysis. When the selected ML classifiers were used to estimate groundwater potential in the Azure cloud computing environment, the DJ and BDT models performed the best in terms of all statistical error measures used (accuracy, precision, recall, F-score, and area under the receiver operating characteristics curve), followed by DF and LD-SVM. The probability of groundwater potential from these algorithms was mapped and visualized into five groundwater potential zones: very low, low, moderate, high, and very high, which correspond to the northern (very low to low), southern (moderate), and middle (high to very high) portions of the study area. Using a cloud computing service provides an improved platform for quickly and cheaply running and testing different algorithms for predicting groundwater potential.

Human health is greatly and directly affected by the quality of groundwater and the extent of its pollution. This research evaluated the quality of groundwater in the Nineveh plain in northern Iraq and determined the suitability of groundwater for drinking purposes. Sixty-nine groundwater samples were taken and the major physical and chemical constituents, including pH, TDS, EC, Ca2+, Mg2+, Na+, K+, Cl−, So42-, HCO3-, and NO3-. were analyzed to use in calculating groundwater quality index for drinking purpose based on the World Health Organization standards for the year 2017. To prevent subjectively assigning weights in the calculation groundwater quality index, the entropy information theory was used. The estimated groundwater quality index values were loaded into ArcGIS 10.8 as a point, shapefile and interpolated using Empirical Bayesian Kriging techniques to produce the final groundwater quality index map of the study area. Results indicated that the entropy groundwater quality index for 2.9% of the samples were within the excellent range, 33% were in the good range, 14.5% were within the moderate range. The groundwater quality index values range between (48-581.8). These values were manually classified into five categories: >200 (very poor), 200-150 (poor), 150-100 (moderate), 100-50 (good), and <50 (excellent). The study discovered that the excellent class occupies 0.2 % (50.9 km2) of the study area, while the good class occupies 23.4% (596 km2), the medium class occupies 18.6 % (473.7 km2), and the poor and extremely poor classes occupy 26.1 % (664.8 km2) and 31.7% (807 km2), respectively.