Designing a Z-scheme rGO-SnS(2) synergistic photocatalyst for photocatalytic mineralization of atrazine and 2,4-dichlorophenoxyacetic acid and applying machine learning for predictive modelling of photocatalytic performance.

The extensive use of agrochemicals for crop protection and quality enhancement has raised environmental concerns due to their negative effects on human health. This study focuses on the design and synthesis of a Z-scheme rGO-SnS(2) photocatalyst for wastewater treatment. rGO-SnS(2) nanocomposites with varying SnS(2) nanoparticle loadings were synthesized using a thermal decomposition method and characterized using various analytical techniques to confirm their composition, phase, structure, morphology, optical properties, and functional groups. The photocatalytic performance of the rGO-SnS(2) nanocomposites was evaluated for the degradation of atrazine (ATZ) and 2,4-dichlorophenoxyacetic acid (2,4-D) in aqueous solutions under natural sunlight. The optimized nanocomposite achieved fast and efficient degradation, with a removal efficiency of 91% for ATZ and 87% for 2,4-D within 3 minutes, compared to only 18% and 26% removal by pure rGO. The study also explored key parameters affecting photocatalytic performance, including catalyst loading, pH, dosage, and regeneration. The degradation pathways and major intermediates of ATZ and 2,4-D were identified using LC-MS analysis, and a detailed reaction mechanism was proposed based on scavenger and mineralization studies. Additionally, machine learning (ML) models, including Gaussian process (GP), artificial neural network (ANN), and support vector machine (SVM), were employed exclusively for predictive analysis of the photocatalytic performance. ANN demonstrated the best predictive capability, with an R (2) value of 0.974 and an error of 0.002. This work highlights the potential of rGO-SnS(2) nanocomposites as effective photocatalysts for agrochemical mineralization, with ML aiding in performance prediction for real-world applications.