Formulating Convolutional Neural Network for mapping total aquifer vulnerability to pollution

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.

Automated summary

This study established an artificial intelligence model based on Convolutional Neural Network to reduce subjectivity in aquifer vulnerability assessment. By applying this model to an unconfined aquifer in northwest Iran, different vulnerability indices were calculated and it was found that despite similar AUC values, significant differences exist in the spatial patterns of the results.