Experimental Analysis and Machine Learning Analysis of Titanium Dioxide and Cobalt Oxide as Photocatalytic Remediation of Indoor Formaldehyde Emissions

Abstract

The presence of volatile organic compounds, such as formaldehyde, in indoor environments has
been identified as a significant contributor to air pollution, thus posing potential health hazards.
This study presents a novel methodology that integrates experimental techniques with machine
learning algorithms to fabricate composite photocatalysts composed of titanium dioxide and
cobalt oxide (TiO2-Co3O4). The goal of this research is to improve the efficiency of formaldehyde
removal in indoor environments. The synthesis of TiO2-Co3O4 heterojunction nanoparticles was
carried out by the process of impregnation. Subsequently, the prepared nanoparticles were
characterized using various analytical techniques, including X-ray diffraction, UV-vis
spectroscopy, and electrochemical impedance spectroscopy. The assessment of photocatalytic
activities was carried out to evaluate the degradation of formaldehyde in the presence of UV light.
The Co3O4 loading, calcination temperature, irradiation intensity, and other parameters were
deliberately and methodically varied. The experimental data were used to train machine learning
models to make predictions about photocatalytic efficiency. The formaldehyde removal efficiency
of the composite photocatalyst with 20 wt% Co3O4 loading was found to be significantly higher
than that of pure TiO2. The cooperation between TiO2 (Co3O4) resulted in the enhancement of light
absorption, charge separation, and surface adsorption. The photocatalyst showed exceptional
stability over five consecutive cycles. Analysis using machine learning techniques successfully
identified the critical factors that can be optimized to achieve the highest possible photocatalytic
performance. The results of this research demonstrate the potential of TiO2- Co3O4 heterojunctions
as highly effective and durable photocatalysts for indoor air purification. The use of an integrated
experimental and computational approach provides valuable insights into the field of designing
optimal photocatalytic devices for mitigating indoor air pollution.