Groundwater vulnerability assessment using AHP-DRASTIC-GALDIT comprehensive model: a case study of Binhai New Area, Tianjin, China

Critical role of vegetation and human activity indicators in the prediction of shallow groundwater quality distribution in Jianghan Plain with LightGBM algorithm and SHAP analysis

Groundwater serves as an indispensable resource for freshwater, but its quality has experienced a notable decline over recent decades. Spatial prediction of groundwater quality (GWQ) can effectively assist managers in groundwater remediation, management, and risk control. Based on the traditional intrinsic groundwater vulnerability (IGV) model (DRASTIC) and three vegetation (V) indicators (NDVI, EVI, and kNDVI) and four human activity (H) indicators (land use, GDP, urbanization index, and nighttime light), we constructed four models for GWQ spatial prediction in the Jianghan Plain (JHP), namely DRASTI, DRASTIH, DRASTIV, and DRASTIVH, excluding the conductivity (C) indicator due to its uniformly low values. LightGBM algorithm, Tree-structured Parzen Estimator (TPE) optimization method, and SHapley Additive exPlanations (SHAP) analysis are used for model setting, calibration, and interpretation, respectively. The results show that nitrogen-related GWQ parameters have higher weights, and the model performs exceptionally well when considering all the indicators (accuracy = 0.840, precision = 0.824, recall = 0.832, F1 score = 0.828, AUROC = 0.914). Notably, the introduced indicators (NDVI, EVI, kNDVI, nighttime light, GDP, and urbanization index) rank as the top six in terms of importance, while traditional DRASTI and land use indicators show lower significance. Based on SHAP analysis, poor GWQ primarily occurs in areas with either extremely high or extremely low GDP and urbanization index values, and human activities are the primary cause of poor GWQ in JHP, potentially involving urbanization, industrial and agricultural activities, as well as fertilizer usage. Finally, the methodological framework proposed in this study is encouraged to be applied to diverse regions, such as plains, karst areas, mountainous regions, and coastal areas, to support effective future groundwater management.

Groundwater salinization risk assessment using combined artificial intelligence models

Assessing the risk of groundwater contamination is of crucial importance for the management of water resources, particularly in arid regions such as Menzel Habib (south-eastern Tunisia). The aim of this research is to create and validate artificial intelligence models based on the original DRASTIC vulnerability methodology to explain groundwater salinization risk (GSR). To this end, several algorithms, such as artificial neural networks (ANN), support vector regression (SVR), and multiple linear regression (MLR), were applied to the Menzel Habib aquifer system. The results obtained indicate that the DRASTIC Vulnerability Index (VI) ranges from 91 to 141 and is classified into two categories: low and moderate vulnerability. However, the correlation between groundwater total dissolved solids (TDS) and the Vulnerability Index is relatively weak (r < 0.5). Indeed, the original DRASTIC index needs some improvements. To improve it, some adjustments are required, notably by incorporating the TDS-groundwater salinization risk (GSR) indicator. The seven parameters of the original DRASTIC model were used as inputs for the artificial intelligence models, while the GSR values were used as outputs. Performance indicators, such as the correlation coefficient (r) and the Willmott Agreement Index (d), showed that the ANN model outperformed the SVR and MLR models. Indeed, during the training phase, the ANN model obtained r values equal to 0.89 and d values of 0.4, demonstrating the superiority, robustness, and accuracy of ANN-based methodologies over the original DRASTIC model. The findings could provide valuable information to guide management of groundwater contamination risks, especially in arid regions.

Comparative study for coastal aquifer vulnerability assessment using deep learning and metaheuristic algorithms

Coastal aquifer vulnerability assessment (CAVA) studies are essential for mitigating the effects of seawater intrusion (SWI) worldwide. In this research, the vulnerability of the coastal aquifer in the Lahijan region of northwest Iran was investigated. A vulnerability map (VM) was created applying hydrogeological parameters derived from the original GALDIT model (OGM). The significance of OGM parameters was assessed using the mean decrease accuracy (MDA) method, with the current state of SWI emerging as the most crucial factor for evaluating vulnerability. To optimize GALDIT weights, we introduced the biogeography-based optimization (BBO) and gray wolf optimization (GWO) techniques to obtain to hybrid OGM-BBO and OGM-GWO models, respectively. Despite considerable research focused on enhancing CAVA models, efforts to modify the weights and rates of OGM parameters by incorporating deep learning algorithms remain scarce. Hence, a convolutional neural network (CNN) algorithm was applied to produce the VM. The area under the receiver-operating characteristic curves for OGM-BBO, OGM-GWO, and VMCNN were 0.794, 0.835, and 0.982, respectively. According to the CNN-based VM, 41% of the aquifer displayed very high and high vulnerability to SWI, concentrated primarily along the coastline. Additionally, 32% of the aquifer exhibited very low and low vulnerability to SWI, predominantly in the southern and southwestern regions. The proposed model can be extended to evaluate the vulnerability of various coastal aquifers to SWI, thereby assisting land use planers and policymakers in identifying at-risk areas. Moreover, deep-learning-based approaches can help clarify the associations between aquifer vulnerability and contamination resulting from SWI.