Assessment of Soil Pollution in The Industrial Zone in South Jeddah Using Pollution Indices and Machine Learning Model | ||||
International Journal of Environmental Studies and Researches | ||||
Volume 2, Issue 4, December 2023, Page 52-67 PDF (1.57 MB) | ||||
Document Type: Original scientific articles | ||||
DOI: 10.21608/ijesr.2023.345999 | ||||
View on SCiNiTO | ||||
Authors | ||||
Adel Salama; Mohamed Azzazy ; Ezzat Elfadaly | ||||
Environmental Studies and Research Institute, University of Sadat City | ||||
Abstract | ||||
Abstract In order to reduce high concentrations of toxic elements in polluted soils, an accurate assessment of the heavy metal concentrations in the industrial city of south Jeddah is required.In this study, the contamination risks for 14 heavy metals, including As, Cd, Co, Cr, Cu, Fe, Mn, Ni, Pb, Zn, Al, Se, and V in the soil, were evaluated using the contamination degree (CD), pollution load index (PLI), potential ecological risk index (RI), and geoaccumulation index (I geo).Support vector machine regression's effectiveness was used to predict the CD, PLI, and RI based on data for the fourteen heavy metals in the soil,. The results showed thatthere were wide variations in the values of the fourteen heavy metals in soil samples, and they are much polluted at this area of study. The I-geo values indicated non-pollution andpollutionby heavy metals.The soil samples were unpolluted (Igeo< 0) by As, Cd, and Se. In contrast, those samples are strongly polluted (Igeo< 3) by Cu, Pb, and Zn.All of the soil samples under investigation were found to be highly contaminated by the examined elements, per CD, RI, and PLI values. The calibration (Cal.) models of support vector machine regression (SVMR) performed the best in predicting the CD and R1 based on trace elements, with R2value of 0.99. The validation (Val.) models performed the best in predicting the CD and RI based on data for f trace elements, with high R2values (0.98 -0.99). | ||||
Keywords | ||||
Keywords: heavy elements; Jeddah; pollution Indices; soil; support vector machine regression | ||||
Statistics Article View: 17 PDF Download: 13 |
||||