Progressive improvement of DRASTICA and SI models for groundwater vulnerability assessment based on evolutionary algorithms

Groundwater management is essential in water and environmental engineering from both quantity and quality aspects due to the growing urban population. Groundwater vulnerability evaluation models play a prominent role in groundwater resource management, such as the DRASTIC model that has been used successfully in numerous areas. Several studies have focused on improving this model by changing the initial parameters or the rates and weights. The presented study investigated results produced by the DRASTIC model by simultaneously exerting both modifications. For this purpose, two land use-based DRASTIC-derived models, DRASTICA and susceptibility index (SI), were implemented in the Shiraz plain, Iran, a semi-arid region and the primary resource of groundwater currently struggling with groundwater pollution. To develop the novel proposed framework for the progressive improvement of the mentioned rating-based techniques, three main calculation steps for rates and weights are presented: (1) original rates and weights; (2) modified rates by Wilcoxon tests and original weights; and (3) adjusted rates and optimized weights using the genetic algorithm (GA) and particle swarm optimization (PSO) algorithms. To validate the results of this framework applied to the case study, the concentrations of three contamination pollutants, NO₃, SO₄, and toxic metals, were considered. The results indicated that the DRASTICA model yielded more accurate contamination concentrations for vulnerability evaluations than the SI model. Moreover, both models initially displayed well-matched results for the SO₄ concentrations, specifically 0.7 for DRASTICA and 0.58 for SI, respectively. Comparatively, the DRASTICA model showed a higher correlation with NO₃ concentrations (0.8) than the SI model (0.6) through improved steps. Furthermore, although both original models demonstrated less correlation with toxic metal concentrations (0.05) compared to SO₄ and NO₃ concentrations, the DRASTICA and SI models with modified rates and optimized weights exhibited enhanced correlation with toxic metals of about 0.7 and 0.2, respectively.