COPPER (II) ADSORPTION ON ACTIVATED CARBON FROM MORINGA WASTE USING ARTIFICIAL NEURAL NETWORK MODELLING IN A CONTINUOUS SYSTEM

Novel materials or techniques for treating wastewater are needed since the presence of developing pollutants in it presents a worldwide environmental issue. This investigation concentrated on turning moringa waste into activated carbon and using it to copper (II) adsorption. Analysis using thermogravimetric revealed the activated carbon's thermal degradation characteristics. BET analysis showed that it had mesoporous properties with increased surface area and pore volumes. The impacts of operating factors including pH, bed depth, concentration, and flow rate were examined using the column approach. The results of the experiment demonstrated that the adsorption capacity rose with input concentration and bed depth and declined with increasing flow rate. The ideal values were discovered to be 40 mg/L for concentration, 5 cm for bed height, and 6 for pH. 30% of the data were used for validation and testing when the ANN technique was developed, with the remaining 70% being used for training. The training dataset's R², MSE, ARE, and RMSE were 0.996, 0.011, 0.048, and 0.021. The curves were analyzed using ANN, and the results revealed that the best ANN architecture for representing the experimental data is consisting of [3 8 1] with the BR algorithm. These findings demonstrate the material's potential to serve as a viable adsorption material for the focused elimination of contaminants, increasing both the application of machine learning in sorption studies as well as the remediation of novel pollutants.