Assessment of the vulnerability of hybrid coastal aquifers: application of multi-attribute decision-making and optimization models

ABSTRACTThis study introduced an innovative hybrid framework using statistical-based, multi-attribute decision-making (MADM), and multi-objective optimization methods to assess the vulnerability of the Oman's Al-Khoud coastal aquifer without temporal variations.. Firstly, an extra parameter, bedrock topography (BT), was added to a commonly used index model, GALDIT and the parameter of aquifer type was removed from the model. Also, the random forest (RF) method was used to define the relative importance of parameters. Then, both frequency ratio (FR) and stepwise weight assessment ratio analysis (SWARA) methods were applied to modify the GALDIT rates. The GALDIT weights were optimized using the non-dominated sorting genetic algorithm-II (NSGA-II). Finally, the coastal aquifer vulnerability index (CAVI) model was obtained based on the hybrid FR-SWARA and NSGA-II models. The CAVI vulnerability map indicated high vulnerability in the Northern aquifer areas. Furthermore, the Spearman correlation coefficient between the CAVI and total dissolved solids (TDS) obtained 0.78.KEYWORDS: coastal aquifer vulnerability index (CAVI)GALDITrandom forest (RF)frequency ratio (FR)stepwise weight assessment ratio analysis (SWARA)non-dominated sorting genetic algorithm-II (NSGA-II) AcknowledgementsThe authors express their thanks to Dr Sharifa and the Environment Authority of Oman, who cooperated by providing the data.Disclosure statementNo potential conflict of interest was reported by the authors.