The availability of groundwater is of concern. The demand for groundwater in Korea increased by more than 100% during the period 1994–2014. This problem will increase with population growth. Thus, a reliable groundwater analysis model for regional scale studies is needed. This study used the geographical information system (GIS) data and machine learning to map groundwater potential in Gangneung-si, South Korea. A spatial correlation performed using the frequency ratio was applied to determine the relationships between groundwater productivity (transmissivity data from 285 wells) and various factors. This study used four topography factors, four hydrological factors, and three geological factors, along with the normalized difference wetness index and land use and soil type. Support vector regression (SVR) and metaheuristic optimization algorithms—namely, grey wolf optimization (GWO), and particle swarm optimization (PSO), were used in the construction of the groundwater potential map. Model validation based on the area under the receiver operating curve (AUC) was used to determine model accuracy. The AUC values of groundwater potential maps made using the SVR, SVR_GWO, and SVR_PSO algorithms were 0.803, 0.878, and 0.814, respectively. Thus, the application of optimization algorithms increased model accuracy compared to the standard SVR algorithm. The findings of this study improve our understanding of groundwater potential in a given area and could be useful for policymakers aiming to manage water resources in the future. Full article

This study aims to develop an integrated approach for mapping and monitoring land use/land cover (LULC) changes and to investigate the impacts of LULC changes and population growth on groundwater level and quality using Landsat images and hydrological information in a Geographic information system (GIS) environment. All Landsat images (1990, 2000, 2010, and 2018) were classified using a support vector machine (SVM) and spectral analysis mapper (SAM) classifiers. The result of validation metrics, including precision, recall, and F1, indicated that the SVM classier has a better performance than SAM. The obtained LULC maps have an overall accuracy of more than 90%. Each pair of enhanced LULC maps (1990–2000, 2000–2010, 2010–2018, and 1990–2018) were used as input data for an image difference algorithm to monitor LULC changes. Maps of change detection were then imported into a GIS environment and spatially correlated against the spatiotemporal maps of groundwater level and groundwater quality. The results also show that the approximate built-up area increased from 227.26 km² (1.39%) to 869.77 km² (7.41%), while vegetated areas (farmlands, parks and gardens) increased from about 76.70 km² (0.65%) to 290.70 km² (2.47%). The observed changes in LULC are highly linked to the depletion in groundwater level and quality across the study area from the Oman Mountains to the coastal areas. Full article

The aim of this research is to introduce a novel ensemble approach using Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR), frequency ratio (FR), and random forest (RF) models for groundwater-potential mapping (GWPM) in Bastam watershed, Iran. This region suffers from freshwater shortages and the identification of new groundwater sites is a critical need. Remote sensing and geographic information system (GIS) were used to reduce time and financial costs of rapid assessment of groundwater resources. Seventeen physiographical, hydrological, and geological groundwater conditioning factors (GWCFs) were derived from a spatial geo-database. Groundwater data were gathered in field surveys and well-yield data were acquired from the Iranian Department of Water Resources Management for 89 locations with high yield potential values ≥ 11 m³ h⁻¹. These data were mapped in a GIS. From these locations, 62 (70%) were randomly selected to be used for model training, and the remaining 27 (30%) were used for validation of the model. The relative weights of the GWCFs were determined with an RF model. For GWPM, 220 randomly selected points in the study area and their final weights were determined with the VIKOR model. A groundwater potential map was created by interpolating the values at these points using Kriging in GIS. Finally, the area under receiver operating characteristic (AUROC) curve was plotted for the groundwater potential map. The success rate curve (SRC) was computed for the training dataset, and the prediction rate curve (PRC) was calculated for the validation dataset. Results of RF analysis show that land use and land cover, lithology, and elevation are the most significant determinants of groundwater occurrence. The validation results show that the ensemble model had excellent prediction performance (PRC = 0.934) and goodness-of-fit (SRC = 0.925) and reasonably high classification accuracy. The results of this study could aid management of groundwater resources and assist planners and decision makers in groundwater-investment planning to achieve sustainability. Full article

Groundwater is one of the most important natural resources, as it regulates the earth’s hydrological system. The Damghan sedimentary plain area, located in the region of a semi-arid climate of Iran, has very critical conditions of groundwater due to massive pressure on it and is in need of robust models for identifying the groundwater potential zones (GWPZ). The main goal of the current research is to prepare a groundwater potentiality map (GWPM) considering the probabilistic, machine learning, data mining, and multi-criteria decision analysis (MCDA) approaches. For this purpose, 80 wells collected from the Iranian groundwater resource department and field investigation with global positioning system (GPS), have been selected randomly and considered as the groundwater inventory datasets. Out of 80 wells, 56 (70%) wells have been brought into play for modeling and 24 (30%) for validation purposes. Elevation, slope, aspect, convergence index (CI), rainfall, drainage density (Dd), distance to river, distance to fault, distance to road, lithology, soil type, land use/land cover (LU/LC), normalized difference vegetation index (NDVI), topographic wetness index (TWI), topographic position index (TPI), and stream power index (SPI) have been used for modeling purpose. The area under the receiver operating characteristic (AUROC), sensitivity (SE), specificity (SP), accuracy (AC), mean absolute error (MAE), and root mean square error (RMSE) are used for checking the goodness-of-fit and prediction accuracy of approaches to compare their performance. In addition, the influence of groundwater determining factors (GWDFs) on groundwater occurrence was evaluated by performing a sensitivity analysis model. The GWPMs, produced by technique for order preference by similarity to ideal solution (TOPSIS), random forest (RF), binary logistic regression (BLR), weight of evidence (WoE) and support vector machine (SVM) have been classified into four categories, i.e., low, medium, high and very high groundwater potentiality with the help of the natural break classification methods in the GIS environment. The very high groundwater potentiality class is covered 15.09% for TOPSIS, 15.46% for WoE, 25.26% for RF, 15.47% for BLR, and 18.74% for SVM of the entire plain area. Based on sensitivity analysis, distance from river, and drainage density represent significantly effects on the groundwater occurrence. validation results show that the BLR model with best prediction accuracy and goodness-of-fit outperforms the other five models. Although, all models have very good performance in modeling of groundwater potential. Results of seed cell area index model that used for checking accuracy classification of models show that all models have suitable performance. Therefore, these are promising models that can be applied for the GWPZs identification, which will help for some needful action of these areas. Full article

This study analyzed the Groundwater Productivity Potential (GPP) of Okcheon city, Korea, using three different models. Two of these three models are data mining models: Boosted Regression Tree (BRT) model and Random Forest (RF) model. The other model is the Logistic Regression (LR) model. The three models are based on the relationship between groundwater-productivity data (specific capacity (SPC) and transmissivity (T)) and the related hydro-geological factors from thematic maps, such as topography, lineament, geology, land cover, and etc. The thematic maps which are generated from the remote sensing images. Groundwater productivity data were collected from 86 wells locations. The resulting GPP maps were validated through area-under-the-curve (AUC) analysis using wells data that had not been used for training the model. When T was used in the BRT, RF, and LR models, the obtained GPP maps had 81.66%, 80.21%, and 85.04% accuracy, respectively, and when SPC was used, the maps had 81.53%, 78.57%, and 82.22% accuracy, respectively. The LR model, which is a statistical model, showed the highest verification accuracy, also the other two models showed high accuracies. These observations indicate that all three models can be useful for groundwater resource development. Full article

Although sampling strategy plays an important role in groundwater potential mapping and significantly influences model accuracy, researchers often apply a simple random sampling method to determine absence (non-occurrence) samples. In this study, an automated, user-friendly geographic information system (GIS)-based tool, selection of absence samples (SAS), was developed using the Python programming language. The SAS tool takes into account different geospatial concepts, including nearest neighbor (NN) and hotspot analyses. In a case study, it was successfully applied to the Bojnourd watershed, Iran, together with two machine learning models (random forest (RF) and multivariate adaptive regression splines (MARS)) with GIS and remotely sensed data, to model groundwater potential. Different evaluation criteria (area under the receiver operating characteristic curve (AUC-ROC), true skill statistic (TSS), efficiency (E), false positive rate (FPR), true positive rate (TPR), true negative rate (TNR), and false negative rate (FNR)) were used to scrutinize model performance. Two absence sample types were produced, based on a simple random method and the SAS tool, and used in the models. The results demonstrated that both RF (AUC-ROC = 0.913, TSS = 0.72, E = 0.926) and MARS (AUC-ROC = 0.889, TSS = 0.705, E = 0.90) performed better when using absence samples generated by the SAS tool, indicating that this tool is capable of producing trustworthy absence samples to improve groundwater potential models. Full article

Dolines are important features strongly influencing the outcomes of groundwater vulnerability maps, subsidence risk and land use studies. Their relationship with subsurface features like epikarst, stresses the importance of doline mapping for environmental and hydrological management strategies. Current methodologies to map dolines from elevation models apply morphometric attributes on depressions, including a depth threshold, to filter depressed areas and to define dolines. However, the use of a single threshold tends to overlook dolines located in already depressed areas. In this work a new geographic information systems (GIS)-based methodology is proposed to identify karst depressions within digital elevation models, applying a multidepth threshold approach. The method statistically classifies depression intervals to identify dolines at variable depths. The method was tested in the Yucatan karst, displaying a final accuracy of 63% after testing different parameters. The results are affected by false positives due to the impossibility of verifying by imagery 190 possible dolines in areas of dense vegetation. Nevertheless, out of 655 estimated dolines, 464 match those located by imagery giving sensitivity and precision values of 85% and 71%, respectively. Comparing this methodology against single threshold outcomes, improvement is evident in doline mapping. Notwithstanding, its application and performance with lower and higher resolution elevation models must be investigated. Full article