Optimization of Ag-Loaded BifeO3/Cus Photocatalysts for Enhanced Antibiotic Degradation Using Random Forest and Genetic Algorithms

Antibiotic pollution in aquatic environments poses major ecological and health hazards., since it fosters bacterial resistance and environmental toxicity. Resolving this issue is essential for protecting aquatic ecosystems and public health. Current photocatalyst models have insufficient prediction accuracy and frequently struggle to respond for dynamic degradation circumstances. This study presents a model aimed at optimising Ag-loaded BiFe03/CuS photo catalysts by combining feature selection through random forests and hyperparameter optimisation using genetic algorithms. The suggested model attained an accuracy of 97%., an F1 score of 0.95., and a recall of 0.94., surpassing established models such as SVM and GBDT. This improved predictive ability not only delivers reliable solutions to complex environmental degradation issues but also ensures scalability for future pollutant-specific applications. The model's effectiveness and adaptability underscore its potential as a premier solution in the domain., enhancing existing approaches for efficiently tackling water pollution and antimicrobial degradation.