The study titled “An investigation on environmental pollution due to essential heavy metals: a prediction model through multilayer perceptrons” led by ITU  Department of Mathematics member Prof. Dr. Murat Sarı was published in International Journal of Phytoremediation.

This study aims to predict heavy metal levels in Robinia pseudoacacia L. plants and soils using an artificial neural network (ANN) approach with ecological parameters to eliminate high cost and time-consuming laboratory procedures. The ANN model estimates concentrations of essential heavy metals (Fe, Mn, Ni) based on Cu and Zn concentrations from plant and soil samples collected from five locations. The model has relative errors ranging from 0.041-0.051, 0.017-0.025, and 0.026-0.029 for Fe, Mn, and Ni, respectively, and including plant parts, location, and Cu/Zn as independent variables reduced relative errors up to 0.007 for Fe, 0.014 for Mn, and 0.022 for Ni. The results can help environmentalists and scientists design optimal study programs for a livable ecosystem.

https://www.tandfonline.com/doi/full/10.1080/15226514.2022.2059056?journalCode=bijp20