Application of Machine Learning (ML) and Artificial Intelligence (AI)-Based Tools for Modelling and Enhancing Sustainable Optimization of the Classical/Photo-Fenton Processes for the Landfill Leachate Treatment

This study presents a machine learning (ML)/artificial intelligence (AI)-based perspective to reliably predict and enhance the treatment efficiency of landfill leachate by classical-Fenton (c-Fenton) photo-Fenton (p-Fenton) processes. experiment also sought lower costs evaluating impact using different numbers UV-c (254 nm) lamps during p-Fenton processes, as well develop sustainable process design for leachate. In modeling stage, radial basis function neural network (RBFN), feed forward (FFNN), support vector regression (SVR) were used results evaluated in broad scanning. Our experimental results, optimized with help genetic algorithm (GA), showed an increasing trend decreasing chemical usage amounts oxidation. The indicate that both techniques performed (classical p-Fenton) within 1 h contact time very high pollutant removal reduction COD approximately 60% 80%, respectively, first 30 min processing. Additionally, it was noted elimination c-Fenton significantly finished 15 min, 52% 73%, respectively. According optimization model, there is increase from 62 82 percent under eight UV compared seven when considering number on p-Fenton. It has been are taken whole, better abilities ML-based models, particularly RBFN FFNN, come fore. From angle, FFNN RBFNN have shown percentile errors extremely close zero MAPE values, error measure independent unit data set, alone. Except two tests whose desirability levels still around 99.99%, all experiments attained outstanding 100.00%. serves more evidence higher performance these approaches.