Vulnerability of a Tunisian Coastal Aquifer to Seawater Intrusion: Insights from the GALDIT Model

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.

Assessing vulnerability of coastal aquifer to seawater intrusion using Convolutional Neural Network

This study examined coastal aquifer vulnerability to seawater intrusion (SWI) in the Shiramin area in northwest Iran. Here, six types of hydrogeological data layers existing in the traditional GALDIT framework (TGF) were used to build one vulnerability map. Moreover, a modified traditional GALDIT framework (mod-TGF) was prepared by eliminating the data layer of aquifer type from the GALDIT model and adding the data layers of aquifer media and well density. To the best of our knowledge, there is a research gap to improve the TGF using deep learning algorithms. Therefore, this research adopted the Convolutional Neural Network (CNN) as a new deep learning algorithm to improve the mod-TGF framework for assessing the coastal aquifer vulnerability. Based on the findings, the CNN model could increase the performance of the mod-TGF by >30 %. This research can be a reference for further aquifer vulnerability studies.

Hybridization of GALDIT method to assess actual and future coastal vulnerability to seawater intrusion

In the recent years, the coastal aquifer of Jijel plain (North Algeria) located on the south of the Mediterranean Sea was utilized for cities growth and agricultural development of the region. Consequently, overexploitation and seawater intrusion were identified as major risks to the groundwater resource. In this work, a new approach integrating groundwater vulnerability method and numerical model for predicting the actual and future seawater is proposed. The groundwater vulnerability assessment has been performed by applying the GALDIT method using GIS and the MODFLOW model was used to simulate the actual and future groundwater level of the aquifer over the period 2020-2050. Three scenarios were simulated under water demand and climate conditions (drought, recharge) to obtain the changes in the groundwater level variation. The results of the GALDIT model application to the actual conditions (year 2020) showed that the high class of groundwater vulnerability is located in the coastal fringe and the terminal stretches of wadis where the seawater intrusion limit is located at a distance range between 840 and 1420 m from the shoreline. However, the results for predicting future groundwater vulnerability showed that the scenario which proposed the artificial recharge basins, although predicting a worrying situation compared to the actual condition, has the best figure of the groundwater vulnerability assessment and seawater intrusion despite the other two scenarios. In this case the limit in the year 2050 is located between distances of 850-1640 m from the shoreline with a forward speed of seawater intrusion of 1-8 m/year, compared to the reference year 2020. This showed that groundwater level variation and recharge were the key factors in controlling groundwater vulnerability to seawater intrusion. The presented new approach can be used to mapping the actual and future groundwater vulnerability assessment to seawater intrusion and groundwater resources management in any coastal areas worldwide.