Lantana trifolia ACTIVATED CARBON FOR REMOVAL OF 2-PHENOXYETHANOIC ACID: NEURAL NETWORK OPTIMIZATION APPROACH

This study uses a low-cost Lantana trifolia-activated carbon and an artificial neural network (ANN) to predict wastewater having 2-phenoxyethanoic acid adsorption. To forecast 2-phenoxyethanoic acid elimination efficiency, MATLAB uses a three-layer feed-forward neural network, a Multilayer Perceptron (MLP), with backpropagation. The neural network is trained with three input parameters: 2-phenoxyethanoic acid concentration, adsorbent amount, and contact duration. Root mean square error and linear regression estimate the removal effectiveness of 2- phenoxyethanoic acid. The findings reveal that the generated ANN models for 2-phenoxyethanoic acid adsorption accurately match empirical data on pollutant removal efficacy. This suggests that low-cost Lantana trifolia activated carbon may be used to estimate 2-phenoxyethanoic acid absorption using the neural network technique.