Spectroscopy and Regression Methods to Predict of Heavy Metals Contamination in Soil: Case Study in Baghdad

Abstract

Heavy metal contamination in soil poses a significant environmental challenge.  Spectroscopy provides a cost-effective, rapid, and reliable method for predicting soil properties, including color, texture, and temperature. This study assesses heavy metal contamination in Baghdad’s soil using spectral data analysis. Forty soil samples were analyzed with an ASD Spectro-radiometer to determine concentrations of As, Cr, Cu, and Zn. X-ray fluorescence (XRF) validated the regression analysis results. Partial least squares regression (PLSR) models effectively predicted Zn and As contamination, achieving R² values of 0.65 and 0.61, with RMSE values of 7 and 94, respectively. These findings confirm the effectiveness of spectroscopy in detecting heavy metals in soil, supporting its use as a reliable tool for environmental monitoring and contamination assessment.