Developing a smart and clean technology for bioremediation of antibiotic contamination in arable lands

This study presents a smart technological framework to efficiently remove azithromycin from natural soil resources using bioremediation techniques. The consists of several modules, each with different models such as Penicillium Simplicissimum (PS) bioactivity, soft computing models, statistical optimisation, Machine Learning (ML) algorithms, and Decision Tree (DT) control system based on Removal Percentage (RP). first module involves designing experiments literature review the Taguchi Orthogonal design method for cultural conditions. RP is predicted function parameters Response Surface Methodology (RSM) three ML algorithms: Instance-Based K (IBK), KStar, Locally Weighted (LWL). sensitivity analysis shows that pH most important factor among all parameters, including pH, Aeration Intensity (AI), Temperature, Microbial/Food (M/F) ratio, Retention Time (RT), p-value <0.0001. AI next significant parameter, also optimal biological conditions removing are temperature 32 °C, 5.5, M/F ratio 1.59 mg/g, 8.59 m3/h. During 100-day process, was found be an insignificant more than 25 days, which simplifies Among IBK model provided accurate prediction RT, correlation coefficient over 95%.