SMART NANOMATERIALS PARTICLES AND AI OPTIMISATION OF SOLAR-POWERED ELECTROCHEMICAL DEHYDRATION OF WATERBORNE CONTAMINANTS

The paper examines an amalgamation of smart nanomaterial-based electrode and
artificial intelligence (AI)-driven optimisation to optimise the solar-powered electrochemical
dehydration of waterborne pollutants. ZnO–TiO₂ on GO (graphene oxide)-
based novel nanocomposites were prepared through hydrothermal and sol-gel methods and have a high surface area (165.2 m²/g) and better electron transfer dynamics. The
solar irradiation (1.0 sun, AM 1.5 G) charged integrated photoelectrochemical cell
showed considerable elimination of contaminants in simulated industrial waste water
comprising of phenol, bisphenol-A and heavy metal ions (Pb²⁺ and Cd²⁺) waste water.
Within 60 min of operation, dehydration efficiencies were found to be 91.8 and 88.3%
in the case of phenol and bisphenol-A, respectively, and more than 96% removal
of Pb²⁺ and Cd²⁺. Optimisation via an AI genetic algorithm-neural network hybrid
model lowered energy consumption by 32.4% compared to when the process was not
optimised, and further the reaction efficiency was maximised by controlling the light
and voltage flux in a dynamic way. FT-IR and XPS characterised the full oxidation
of phenolic intermediates CO₂ and H₂O. After 100 cycles, there was a stable performance
of the system with the degradation of electrodes being insignificant (< 2.1%
efficiency decrease). This finding indicates the promise of smart material-AI to realise
scalable, green, and energy-efficient water purification technology, with applications
to next-generation solar-electrochemical remediation systems.