Decolourization of bromocresol green dye solution by acid functionalized rice husk: Artificial intelligence modeling, GA optimization, and adsorption studies

Novel application and comparison of intelligent models such as adaptive neuro-fuzzy inference systems (ANFIS), artificial neural network (ANN), and response surface methodology (RSM) in adsorptive removal of bromocre-sol green (BCG) dye via acid functionalized rice husk (AFRH) was the crux of this work. Tetraoxophosphate V acid was used in preparing the AFRH. The effects of process parameters such as initial concentration, solution pH, adsorbent dosage, temperature, and contact time were investigated. The synthesized AFRH was character-ized via Scanning Electron Microscope (SEM) and Fourier Transform Infrared (FTIR) spectrophotometer. Genetic algorithm (GA) optimization tool was used in optimizing the process parameters. The result showed that tem-perature was the most influential parameter in the removal of BCG dye. The predictive modeling of the RSM, ANN and ANFIS models demonstrated good correlation with R 2 of 0.9325, 0.9797 and 0.9987 respectively. Low values of calculated error functions of RMSE (ANFIS = 0.0025; RSM= 0.01899 and ANN= 0.01028) and HYBRID (ANFIS = 0.0006; RSM= 0.03216 and ANN= 0.00943) indicated good harmony between experimental values and models' predictions. Validated GA optimization yielded maximum adsorption capacities of 139.23, 136.29, and 137.14 mg/g for ANFIS-GA, RSM-GA, and ANN-GA respectively. The result showed that the order of the models' effectiveness for BCG removal is: ANFIS > ANN > RSM. Isotherm study revealed that Freundlich isotherm with R 2 of 0.999 best described the equilibrium modeling while the kinetic analysis indicated that pseudo second order ( R 2 = 0.998) and Elovich ( R 2 = 0.995) models best accounted for the kinetics of the experimental data. Thermodynamics study denoted that the adsorption process was endothermic and spontaneous. A point of zero charge of 4.65 was obtained. The results of this present work highlighted the potential of the synthesized AFRH in effectively treating BCG dye contaminated wastewater using the optimized conditions.

Automated summary

The novel application and comparison of intelligent models, including adaptive neuro-fuzzy inference systems (ANFIS), artificial neural network (ANN), and response surface methodology (RSM), in the adsorptive removal of bromocre-sol green (BCG) dye using acid functionalized rice husk (AFRH) was the main focus of this study. The effects of various process parameters were investigated, and the AFRH was characterized using SEM and FTIR. Optimization with genetic algorithm (GA) showed that temperature was the most influential parameter. The RSM, ANN, and ANFIS models demonstrated good correlation and low error functions, with ANFIS performing the best in BCG removal. Freundlich isotherm best described the equilibrium modeling, and pseudo second-order and Elovich models best accounted for the kinetics. Thermodynamics study indicated that the adsorption process was endothermic and spontaneous. The results highlighted the potential of AFRH in effectively treating BCG dye contaminated wastewater.