Heavy metals distribution and ecological risk assessment including arsenic resistant PGPR in tidal mangrove ecosystem.

Heavy metals (HM) are the major proximate drivers of pollution in the mangrove ecosystem. Therefore, ecological risk (ER) due to HM distribution/concentration in core-sediment of Puzi mangrove region (Taiwan) was examined with tidal influence (TI) along with indigenous rhizospheric bacteria (IRB). The HM concentration was observed higher at active-tidal-sediment compared to partially-active-sediment. Geo-accumulation index (Igeo) and contamination factor (CF) indicated the tidal-sediment was highly contaminated with arsenic (As) and moderately contaminated with Lead (Pb) and Zinc (Zn). However, the pollution loading index (PLI) and degree of contamination (Cd) exhibited 'no pollution' and 'low-moderate degree of contamination', in the studied region respectively. The isolated IRB (Priestia megaterium, Bacillus safenis, Bacillus aerius, Bacillus subtilis, Bacillus velenzenesis, Bacillus lichenoformis, Kocuria palustris, Enterobacter hormaechei, Pseudomonus fulva, and Paenibacillus favisporus; accession number OM979069-OM979078) exhibited the arsenic resistant behavior with plant-growth-promoting characters (IAA, NH3, and P-solubilization), which can be used in mangrove reforestation and bioremediation of HM.

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.