Artificial neural network based study for photocatalytic degradation of dyes in the presence of 3d transition metal doped zno
Loading...
Date
2023
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
UMT, Lhr
Abstract
Extensive research has been carried out on the degradation of organic pollutants through photocatalysis due to the increasing demand for wastewater that is free from pollutants. The results obtained from different experimental runs in photocatalytic degradation can be utilized in data-centric machine learning modeling methods like artificial neural networks. The optimization of 3d transition metal dopants for enhancing the photocatalytic degradation of dyes represents a promising approach in the field of environmental remediation. This study aims to leverage the power of neural networks to optimize the impact of such dopants on the mechanism of photocatalytic degradation. The photocatalytic degradation process is described using both Artificial Neural Networks (ANN). These models incorporated six degradation variables, namely the concentration of composite, concentration of the dye, temperature, pH, irradiation time, and the light intensity or wavelength, as input variables. It uses the degradation percentage of the dye as their output variable. By training neural networks on a comprehensive dataset of experimental observations, the relationships between various process parameters, dopant types, and the efficiency of dye degradation will be modeled and analyzed. The maximum R2 for the outcomes of this research can significantly contribute to the development of more efficient photocatalytic systems for dye removal, ultimately leading to improved environmental sustainability