Nadiri Ata Allah, Moazamnia Marjan, Sadeghfam Sina, Gnanachandrasamy Gopalakrishnan, Venkatramanan Senapathi
Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz, 29 Bahman Boulevard, Tabriz, 166616471, East Azerbaijan, Iran; Institute of Environment, University of Tabriz, Tabriz, 5166616471, East Azerbaijan, Iran; Traditional Medicine and Hydrotherapy Research Center, Ardabil University of Medical Sciences, Ardabil, 5618985991, Ardabil, Iran; Medical Geology and Environmental Research Center, University of Tabriz, Iran.
Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz, 29 Bahman Boulevard, Tabriz, 166616471, East Azerbaijan, Iran.
Environ Pollut. 2022 Jul 1;304:119208. doi: 10.1016/j.envpol.2022.119208. Epub 2022 Mar 26.
Aquifer vulnerability mapping to pollution is topical research activity, and common frameworks such as the basic DRASTIC framework (BDF) suffer from the inherent subjectivity. This paper formulates an artificial intelligence modeling strategy based on Convolutional Neural Network (CNN) to decrease subjectivity. This formulation considers three definitions of intrinsic, specific, and total vulnerabilities. Accordingly, three CNN models are trained and tested to calculate IVI, SVI, and TVI, respectively referring to the intrinsic, specific, and total vulnerability indices. The formulation is applied in an unconfined aquifer northwest of Iran and delineates hotspots within the aquifer. The area under curve (AUC) values derived by the receiver operating curves evaluate the vulnerability indices versus nitrate concentrations. The AUC values for BDF, IVI, SVI, and TVI are 0.81, 0.91, 0.95, and 0.95, respectively. Therefore, CNNs significantly improve the results compared to BDF, but IVI, SVI, and TVI have approximately identical performances. However, the visual comparison between their results provides evidence that significant differences exist between the spatial patterns despite identical AUC values.
