Machine Learning‐Assisted Piezo‐Photocatalytic Performance of Green‐Derived ZnO Nanofibrous Matrix for Wastewater Treatment

Abstract

The increasing discharge of persistent organic dyes from industrial effluents into aquatic environments poses a serious threat to ecological systems and human health. It is essential to develop sustainable and efficient remediation technologies for the treatment. For this, we present a novel approach to green‐synthesized zinc oxide (ZnO) nanoparticles using turmeric extract as a reducing and passivating agent, followed by electrospinning for nanofiber synthesis. The integration of green‐synthesized ZnO nanoparticles with the PLA matrix as a catalyst yielded well‐defined morphologies and crystallinity, as confirmed through detailed characterization. The synthesized PLA‐ZnO nanofibers exhibited remarkable photocatalytic and piezocatalytic activities for the decolourization of anionic and cationic dyes under light and mechanical vibrations. In addition, nanofibers exhibited significant antibacterial properties against both Gram‐negative Escherichia coli (E. coli) and Gram‐positive Staphylococcus aureus (S. aureus). In our endeavor to understand the relationship between wavelength, time, and absorbance shown by PLA‐ZnO nanofibers in dye decolorization, among other variables, we studied the behavior of multiple machine learning (ML) models, including linear methods, decision‐tree‐based models, support vector regression (SVR), and a neural network regressor. Due to the exceptional efficacy of PLA‐ZnO nanofibers and ML predictions, it holds substantial promise for innovative applications in environmental remediation.