Explore the vast range of titles available.

Many major cities worldwide have inevitably experienced excessive groundwater pumping due to growing demands for freshwater in urban development. To mitigate land subsidence problems during urbanization, various regulations have been adopted to control groundwater usage. This study examines the transition in the post‐subsidence stage, especially in metropolitan areas, to adaptively adjust subsidence prevention strategies for effective groundwater management. Taking the Taipei Basin as an example, historical data reveals significant subsidence of more than 2 m during early urban development, with subsidence hazards largely mitigated over decades. However, the rising groundwater level poses a risk to the stability of engineering excavations. In this study, 29 X‐band Cosmo‐Skymed constellation (CSK) images were utilized with the Persistent Scatterer InSAR (PSInSAR/PSI) technique to monitor surface displacements during the construction of the Mass Rapid Transit system. Correlating groundwater levels helps identify the heterogeneous hydrogeological environment, and the potential groundwater capacity is assessed. PSI time‐series reveal that approximately 2 cm of recoverable land displacements correspond to groundwater fluctuations in the confined aquifer, indicative of the typically elastic behavior of the resilient aquifer system. The estimated groundwater storage variation is about 1.6 million cubic meters, suggesting this potential groundwater capacity could provide available water resources with proper management. Additionally, engineering excavation safety can be ensured with lowered groundwater levels. This study emphasizes the need to balance groundwater resource use with urban development by adjusting subsidence prevention and control strategies to achieve sustainable water management in the post‐subsidence stage. Plain Language Summary Groundwater is used as an important freshwater resource in global urban development, but over‐exploitation often leads to subsidence problems. Once land subsidence situation is under controlled, attention turns to how to balance urban development with environmental protection. This study takes a metropolitan area in a post‐subsidence period as an example and uses satellite technique to estimate potential groundwater volumes. It suggests that with proper management, groundwater resources can be fully utilized and related engineering disasters can be prevented. Key Points Integrating InSAR and numerical model for transient‐like state groundwater level mapping Quantifying changes in potential groundwater storage as available freshwater resources Efficient groundwater utilization for achieving sustainability in post‐subsidence stages

Groundwater resources can be expected to be increasingly relied upon in the near future, as a consequence of rapid population growth and global environmental change. Cost-effective and efficient techniques for groundwater exploration are gaining recognition as tools to underpin hydrogeological surveys in mid- and low-income regions. This paper provides a state of the art on groundwater potential mapping, an explorative technique based on remote sensing and geographical databases that has experienced major developments in recent years. A systematic review of over 200 directly relevant papers is presented. Twenty variables were found to be frequently involved in groundwater potential investigations, of which eight are almost always present: geology, lineaments, landforms, soil, land use/land cover, rainfall, drainage density, and slope. The more innovative approaches draw from satellite images to develop indicators related to vegetation, evapotranspiration, soil moisture and thermal anomalies, among others. Data integration is carried out either through expert judgement or through machine-learning techniques, the latter being less common. Three main conclusions were reached: (1) for optimal results, groundwater mapping must be used as a tool to complement field work, rather than a low-cost substitute; (2) the potential of remote-sensing techniques in groundwater exploration is enormous, particularly when the power of machine learning is harnessed by involving human judgement; (3) quality assurance remains the main challenge ahead, as exemplified by the fact that a majority of the existing studies in the literature lack adequate validation.

Identifying areas with high groundwater potential is important for groundwater resources management. The main objective of this study is to propose a novel classifier ensemble method, namely Random Forest Classifier based on Random Subspace Ensemble (RS-RF), for groundwater potential mapping (GWPM) in Qorveh-Dehgolan plain, Kurdistan province, Iran. A total of 12 conditioning factors (slope, aspect, elevation, curvature, stream power index (SPI), topographic wetness index (TWI), rainfall, lithology, land use, normalized difference vegetation index (NDVI), fault density, and river density) were selected for groundwater modeling. The least square support vector machine (LSSVM) feature selection method with a 10-fold cross-validation technique was used to validate the predictive capability of these conditioning factors for training the models. The performance of the RS-RF model was validated using the area under receiver operating characteristic curve (AUROC), success and prediction rate curves, kappa index, and several statistical index-based measures. In addition, Friedman and Wilcoxon signed-rank tests were used to assess statistically significant level among the new model with the state-of-the-art soft computing benchmark models, such as random forest (RF), logistic regression (LR) and naïve Bayes (NB). Results showed that the new hybrid model of RS-RF had a very high predictive capability for groundwater potential mapping and exhibited the best performance among other benchmark models (LR, RF, and NB). Results of the present study might be useful to water managers to make proper decisions on the optimal use of groundwater resources for future planning in the critical study area.

Considering the unstable condition of water resources in Iran and many other countries in arid and semi-arid regions, groundwater studies are very important. Therefore, the aim of this study is to model groundwater potential by qanat locations as indicators and ten advanced and soft computing models applied to the Beheshtabad Watershed, Iran. Qanat is a man-made underground construction which gathers groundwater from higher altitudes and transmits it to low land areas where it can be used for different purposes. For this purpose, at first, the location of the qanats was detected using extensive field surveys. These qanats were classified into two datasets including training (70%) and validation (30%). Then, 14 influence factors depicting the region’s physical, morphological, lithological, and hydrological features were identified to model groundwater potential. Linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), flexible discriminant analysis (FDA), penalized discriminant analysis (PDA), boosted regression tree (BRT), random forest (RF), artificial neural network (ANN), K-nearest neighbor (KNN), multivariate adaptive regression splines (MARS), and support vector machine (SVM) models were applied in R scripts to produce groundwater potential maps. For evaluation of the performance accuracies of the developed models, ROC curve and kappa index were implemented. According to the results, RF had the best performance, followed by SVM and BRT models. Our results showed that qanat locations could be used as a good indicator for groundwater potential. Furthermore, altitude, slope, plan curvature, and profile curvature were found to be the most important influence factors. On the other hand, lithology, land use, and slope aspect were the least significant factors. The methodology in the current study could be used by land use and terrestrial planners and water resource managers to reduce the costs of groundwater resource discovery.

Flood is one of the most common natural disasters worldwide. The aim of this study was to evaluate the application of the Dempster–Shafer-based evidential belief function (EBF) for spatial prediction of flood-susceptible areas in Brisbane, Australia. This algorithm has been tested in landslide and groundwater mapping; however, it has not been examined in flood susceptibility modelling. EBF has an advantage over other statistical methods through its capability of evaluating the impacts of all classes of every flood-conditioning factor on flooding and assessing the correlation between each factor and flooding. EBF outcomes were compared with the results of well-known statistical methods, including logistic regression (LR) and frequency ratio (FR). Flood-conditioning factor data set consisted of elevation, aspect, plan curvature, slope, topographic wetness index (TWI), geology, stream power index (SPI), soil, land use/cover, rainfall, distance from roads and distance from rivers. EBF produced the highest prediction rate (82.60%) among all the methods. The research findings may provide a useful methodology for natural hazard and land use management.

Groundwater resources are vitally important in arid and semi-arid areas meaning that spatial planning tools are required for their exploration and mapping. Accordingly, this research compared the predictive powers of five machine learning models for groundwater potential spatial mapping in Wadi az-Zarqa watershed in Jordan. The five models were random forest (RF), boosted regression tree (BRT), support vector machine (SVM), mixture discriminant analysis (MDA), and multivariate adaptive regression spline (MARS). These algorithms explored spatial distributions of 12 hydrological-geological-physiographical (HGP) conditioning factors (slope, altitude, profile curvature, plan curvature, slope aspect, slope length (SL), lithology, soil texture, average annual rainfall, topographic wetness index (TWI), distance to drainage network, and distance to faults) that determine where groundwater springs are located. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was employed to evaluate the prediction accuracies of the five individual models. Here the results were ranked in descending order as MDA (83.2%), RF (80.6%), SVM (80.2%), BRT (78.0%), and MARS (75.5%).The results show good potential for further use of machine learning techniques for mapping groundwater spring potential in other places where the use and management of groundwater resources is essential for sustaining rural or urban life.

Groundwater mapping is essential for meeting the water requirement of people. Identification of groundwater potential zone was attempted for a watershed located in Kanchipuram district, Tamil Nadu, India. The Landsat 8 and Landsat 5 data were used for land use/land cover analysis. For delineating groundwater potential zone, total seven thematic layers namely drainage density, slope, geology, soil, geomorphology, rainfall, land use/land cover and observed groundwater levels were considered during the analysis. Afterwards thematic layers were converted into raster using GIS platform. Further, after assigning weights and ratings to each thematic layer, overlay analysis was applied and total five zones were delineated as very good, good, moderate, poor, and very poor. The majority of area has moderate groundwater potential zone. The potential zone map was also validated using ROC method. The map of 2005 shows a highest accuracy compared to rest year maps.

Groundwater is an essential part of the water supply worldwide, and the demands on this water source can be expected to increase in the future. To satisfy the need for resources and to ensure sustainable use of resources, increasingly detailed knowledge of groundwater systems is necessary. However, it is difficult to directly map groundwater with well-established geophysical methods as these are sensitive to both lithology and pore fluid. Surface nuclear magnetic resonance (SNMR) is the only method with a direct sensitivity to water, and it is capable of non-invasively quantifying water content and porosity in the subsurface. Despite these attractive features, SNMR has not been widely adopted in hydrological research, the main reason being an often-poor signal-to-noise ratio, which leads to long acquisition times and high uncertainty in terms of results. Recent advances in SNMR acquisition protocols based on a novel steady-state approach have demonstrated the capability of acquiring high-quality data much faster than previously possible. In turn, this has enabled high-density groundwater mapping with SNMR. We demonstrate the applicability of the new steady-state scheme in three field campaigns in Denmark, where more than 100 SNMR soundings were conducted with a depth of investigation of approximately 30 m. We show how the SNMR soundings enable us to track water level variations at the regional scale, and we demonstrate a high correlation between water levels obtained from SNMR data and water levels measured in boreholes. We also interpret the SNMR results jointly with independent transient electromagnetic (TEM) data, which allows us to identify regions with water bound in small pores. Field practice and SNMR acquisition protocols were optimized during the campaigns, and we now routinely measure high-quality data at 8 to 10 sites per day with a two-person field crew. Together, the results from the three surveys demonstrate that, with steady-state SNMR, it is now possible to map regional variations in water levels with high-quality data and short acquisition times.

A data-driven modelling approach was applied to quantify the potential groundwater yield from weathered crystalline basement aquifers in West Africa, which are a strategic resource for achieving water and food security. To account for possible geological control on aquifer productivity, seven major geological domains were identified based on lithological, stratigraphic, and structural characteristics of the crystalline basement. Extensive data mining was conducted for the hydrogeological parameterisation that led to the identification of representative distributions of input parameters for numerical simulations of groundwater abstractions. These were calibrated to match distributions of measured yields for each domain. Calibrated models were then applied to investigate aquifer and borehole scenarios to assess groundwater productivity. Considering the entire region, modelling results indicate that approximately 50% of well-sited standard 60-m-deep boreholes could sustain yields exceeding 0.5 L/s, and 25% could sustain the yield required for small irrigation systems (> 1.0 L/s). Results also highlighted some regional differences in the ranges of productivities for the different domains, and the significance of the depth of the static water table and the lateral extent of aquifers across all geological domains. This approach can be applied to derive groundwater maps for the region and provide the quantitative information required to evaluate the potential of different designs of groundwater supply networks.

The main goal of this study was to optimize an adaptive neuro-fuzzy inference system (ANFIS) using three meta-heuristic optimization algorithms—genetic algorithm (GA), biogeography-based optimization (BBO) and simulated annealing (SA)—to prepare groundwater potential maps. The methodology was applied to the Booshehr plain, Iran. The results of optimized models were compared with ANFIS individually and three bivariate models: frequency ratio (FR), evidential belief function (EBF), and the entropy model. First, 339 wells with groundwater yield higher than 11 m3/h were selected and randomly divided into two groups. In all, 238 wells (70%) were used for training the models and 101 wells (30%) were used for testing and validating the models. Fifteen conditioning factors were selected as input parameters for the modeling. The accuracy of the groundwater potential maps for the study area was determined using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and standard deviation of error (SD), as well as the area under the receiver operating characteristic (ROC) curve (AUC). Overall, the results demonstrated that ANFIS-GA had the highest prediction capability (AUC = 0.915) for groundwater potential mapping followed by ANFIS-BBO (0.903), entropy (0.862), FR (0.86), ANFIS-SA (0.83), ANFIS (0.82) and EBF (0.80). According to the entropy model, land-use, soil order and rainfall factors had the highest impact on groundwater potential in the study area. The results of this research show that the ANFIS models combined with meta-heuristic optimization algorithms can be a useful decision-making tool for assessment and management of groundwater resources.