Environmental Assessment of Potentially Toxic Elements Using Pollution Indices and Data-Driven Modeling in Surface Sediment of the Littoral Shelf of the Mediterranean Sea Coast and Gamasa Estuary, Egypt

Coastal environmental assessment techniques have evolved into one of the most important fields for long-term development and management coastal zones. So, overall aim present investigation was to provide effective approaches making informed decisions about Gamasa coast sediment quality. Over a two-year investigation, samples were meticulously collected from estuary littoral shelf. The inductively coupled plasma mass spectra (ICP-MS) used total concentrations Al, Fe, Ti, Mg, Mn, Cu, P, V, Ba, Cr, Sr, Co, Ni, Zn, Pb, Zr, Ce. Single elements pollution indices including geoaccumulation index (Igeo), contamination factor (CF), enrichment (EF), as well multi-elements comprising potential ecological risk (RI), degree (Dc), load (PLI) assess various geo-environmental variables affecting Mediterranean system. Furthermore, Dc, PLI, RI estimated using random forest (RF) Back-Propagation Neural Network (BPNN) depending on selected elements. According Dc results, all investigated categories considerably contaminated. Mn showed remarkable in originated anthropogenic sources based CF, EF, Igeo data. Moreover, findings revealed that tested pose low ecologically risk. Meanwhile, 70% polluted, while 93.75% shelf unpolluted. BPNNs -PCs-CD-17 model performed best demonstrated better association between exceptional qualities CD. With R2 values 1.00 calibration (Cal.) validation (Val.). -PCs-PLI-17 models terms measuring PLI with respective 0.98 Cal. Val. datasets. RF BPNN may be precisely quantify (Dc, RI) (Val.) datasets utilizing potentially toxic surface sediment.