Utilizing machine learning to evaluate heavy metal pollution in the world's largest mangrove forest.

The world's largest mangrove forest (Sundarbans) is facing an imminent threat from heavy metal pollution, posing grave ecological and human health risks. Developing an accurate predictive model for heavy metal content in this area has been challenging. In this study, we used machine learning techniques to model sediment pollution by heavy metals in this vital ecosystem. We collected 199 standardized sediment samples to predict the accumulation of eleven heavy metals using ten different machine learning algorithms. Among them, the extremely randomized tree model exhibited the best performance in predicting Fe (0.87), Cr (0.89), Zn (0.85), Ni (0.83), Cu (0.87), Co (0.62), As (0.68), and V (0.90), achieving notable R2 values. On the other hand, the random forest outperformed for predicting Cd (0.72) and Mn (0.91), whereas the decision tree model showed the best performance for Pb (0.73). The feature attribute analysis identified FeV, CrV, CuZn, CoMn, PbCd, and AsCd relationships resembled with correlation coefficients among them. Based on the established models, the prediction of the contamination factor of metals in sediments showed very high Cd contamination (CF ≥ 6). The Moran's I index for Cd, Cr, Pb, and As were 0.71, 0.81, 0.71, and 0.67, respectively, indicating strong positive spatial autocorrelation and suggesting clustering of similar contamination levels. Conclusively, this research provides a comprehensive framework for predicting heavy metal sediment pollution in the Sundarbans, identifying key areas needing urgent conservation. Our findings support the adoption of integrated management strategies and targeted remedial actions to mitigate the harmful effects of heavy metal contamination in this vital ecosystem.

Sedimentary geochemistry mediated by a specific hydrological regime in the water level fluctuation zone of the Three Gorges Reservoir, China.

The water level fluctuation zone (WLFZ) of the Three Gorges Reservoir (TGR) acts as an important sink for inflowing suspended sediment loads over the inundation periods following regular dam operations. This study depicts the sedimentary geochemical dynamics along a sedimentary profile based on the determined chronology and explores its links to the specific hydrological regime created by dam flow regulation and riverine seasonal suspended sediment dynamics. A compact 345-cm-long sediment core was extracted near the base water level (145.3 m) from the WLFZ of the TGR and sectioned at 5-cm intervals. Extracted sediment subsamples were analyzed for grain size composition, organic matter (OM), total nitrogen (TN), and geochemical elements (Na, K, Ca, Mg, Pb, Zn, Ni, Co, Mn, Cr, Fe, and Cu). The sediment core chronology was determined using 137Cs elemental analysis. Sedimentary geochemistry and grain size properties of extracted sediment core exhibited greater variations during initial submergence years till the first complete impoundment of the TGR (2006-2010). Afterward (2011-2013), although upstream inflowing suspended sediments and reservoir water level were comparable, sediment deposition and concentrations of sedimentary geochemical constituents showed considerably fewer variations. Seasonal variations in sediment deposition and geochemical composition were also observed during the rainy (October-April) and dry (May-September) seasons, in addition to annual variations. Grain size, OM, and other sediment geochemical constituents all had significant correlations with each other and with sediment core depth. The concentrations of geochemical elements in various sediment stratigraphic layers exhibited staggering associations with each other and were dependent on each other in several ways. The arrangement of geochemical elements in various stratigraphic layers of the extracted core illustrated amalgamation with inputs from upstream seasonal suspended sediment dynamics and reservoir water levels. During shortened submergence periods and higher input sediment loads, geochemical elements demonstrated impulsive distributions. Alternatively, during longer submergence periods, elemental distributions were relatively uniform attributed to higher settling time to deposit according to grain size and geochemical affinities. Higher suspended sediment loads in association with seasonal floods also resulted in rough sediment deposition patterns, imparting variations in the distributions of geochemical elements. Interim mediations in geochemical element concentrations are associated with seasonal distal flash floods and local terrace bank collapses, which generate significant amounts of distal sediment loads that are quickly deposited and are not sorted hydrodynamically. Overall, although a specific mechanism was devised to circumvent the siltation process, a considerable amount of sediment is trapped at pre-dam sites. In addition, siltation caused nutrients and geochemical elements' enrichment.