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.

Groundwater quality for irrigation in an arid region-application of fuzzy logic techniques.

Groundwater is the main source to answer the irrigation supply in several arid and semi-arid areas. In the present work, groundwater quality for irrigation purposes in the arid region of Menzel Habib (Tunisia) for thirty-six groundwater samples is assessed considering the application of different conventional water quality indicators, particularly, electrical conductivity (EC), sodium absorption ratio (SAR), soluble sodium percentage (SSP), magnesium adsorption ratio (MAR), Kelly ratio (KR), and permeability index (PI). The results obtained indicate a variability for EC: 3.06 to 14.98 mS.cm-1; SAR: 4.08 to 19.30; SSP: 35.78 to 71.53%; MAR: 34.19 to 56.01; PI: 38.47 to 72.74; and KR: 0.56 to 2.47. These results suggest that groundwater from Menzel Habib aquifer system is classified between excellent to unsuitable according to the applied water quality indices. Furthermore, the groundwater samples are also plotted in the Richards diagram classification system, based on the relation between SAR and EC, suggesting that almost groundwater samples present a harmful quality. Moreover, fuzzy logic model has been proposed and created to assess groundwater quality for irrigation. The membership functions are constructed for six significant parameters such as EC, SAR, SSP, MAR, KR, and PI and the rules are, then, fired to get a simple Fuzzy Irrigation Water Quality Index (FIWQI). The obtained groundwater quality results suggest that 3% of the samples from Menzel Habib region are considered as "good" for irrigation, 3% are classified as "good to permissible", 33% with a "permissible" quality, 36% "permissible to unsuitable", while 25% of groundwater present an "unsuitable" quality. Thus, the use of fuzzy logic techniques has more reliable and robust results by overcoming the uncertainties in the decision-making attributed to the conventional methods by the creation of new classes (excellent to good, good to permissible, and permissible to unsuitable) in addition to the classes proposed by Richards diagram classification (excellent, good, permissible, and unsuitable) to assess the groundwater quality suitability for irrigation purposes.

Integration of water contamination indicators and vulnerability indices on groundwater management in Menzel Habib area, south-eastern Tunisia.

Groundwater salinization is a major problem throughout arid and semi-arid areas due to different natural processes and anthropogenic activities and has caused irreparable environmental and economic effects. The objective of this study is to evaluate groundwater vulnerability of Menzel Habib which has been firstly assessed using multiple methods such as DRASTIC, DRASTIC pesticide, SINTACS and SI models. These indices are based on combination of intrinsic and specific characteristics of the aquifer. Almost the area presents a low to moderate vulnerability with the highest vulnerability on the western region, associated to lower deep of groundwater and evaporation processes, with consequent salinity increase. Total Dissolved solids, chloride, sodium, sulfate, calcium, and magnesium water contents were determined in a total of twenty-five groundwater samples from Menzel Habib aquifer. The accuracy of the best robust model was evaluated by the correlation between the different vulnerability indices and contamination water indicators. The main aim of this study is the development of a modified vulnerability index, DRASTIC_Sal, which includes the contribution of total dissolved solids from Menzel Habib groundwater. DRASTIC_Sal index is a simple approach for aquifer salinization vulnerability assessment, particularly for inland aquifers from arid and semi-arid regions with associated agricultural activities.