Adsorptive Removal of Methylene Blue (MB) from Wastewater: A Comparative Modeling Study Utilizing RSM, ANN, and ANFIS Model

Abstract:

The exceptional properties of chitosan and its effective technique of adsorbing contaminants even to near-zero concentrations are the primary reasons for special attention. The adsorption studies analyzed various elements, including pH, concentration, contact time, and adsorbent dose. The study used these factors as input data, with the output data concentrating on MB removal efficiency. For prediction and optimization, MB adsorption used response surface methodology/central composite design (RSM-CCD), artificial neural network (ANN), and adaptive neuron-fuzzy inference system (ANFIS) models. For developing the ANN and ANFIS models, 70% of the data was allocated for training, and 15% was dedicated to validation and testing. Based on the RSM-CCD findings, the optimization outcome for the process parameters was obtained at pH 7, contact time 55 minutes, 6.0 grams of adsorbent, and MB concentration of 125 mg/L. However, an ideally trained neural network is described using training, testing, and validation phases, and the R² values at these phases were found to be 0.99987, 1, and 1, respectively. The statistical findings showed that the ANFIS approach outperforms the RSM and ANN model approaches.

• Periodical: Engineering Chemistry (Volume 9)
• Pages: 85-92
• DOI: https://doi.org/10.4028/p-Z9rTBB
• Online since: March 2025
• Authors: Ephraim Igberase*, Innocentia Mkhize
• Keywords: Adsorption, Neural Network, Removal Efficiency, Response Surface

References

[1] A. Mokhtar, S. Abdelkrim, A. Djelad, A. Sardi, B. Boukoussa, M. Sassi, A. Bengueddach, Adsorption behavior of cationic and anionic dyes on magadiite-chitosan composite beads, Carbohydr Polym 229 (2020).

DOI: 10.1016/j.carbpol.2019.115399

[2] J. Geng, L. Lin, F. Gu, J. Chang, Adsorption of Cr(Ⅵ) and dyes by plant leaves: Effect of extraction by ethanol, relationship with element contents and adsorption mechanism, Ind Crops Prod 177 (2022).

DOI: 10.1016/J.INDCROP.2022.114522

[3] A. Mokhtar, B. Boukoussa, A. Baba Ahmed, S. Abdelkrim, A. Djelad, M. Hachemaoui, F. Zaoui, A. Bengueddach, M. Sassi, Alginate@Layered Silicate Composite Beads: Dye Elimination, Box–Behnken Design Optimization and Antibacterial Property, J Inorg Organomet Polym Mater 32 (2022) 2615–2633.

DOI: 10.1007/s10904-022-02350-9

[4] L.D. Pompeu, P.C.L. Muraro, G. Chuy, B.S. Vizzotto, G. Pavoski, D.C.R. Espinosa, L. da Silva Fernandes, W.L. da Silva, Adsorption for rhodamine b dye and biological activity of nano-porous chitosan from shrimp shells, Environ Sci and Pollut Res 29 (2022) 49858–49869.

DOI: 10.1007/s11356-022-19259-y

[5] A. Mokhtar, S. Abdelkrim, B. Boukoussa, M. Hachemaoui, A. Djelad, M. Sassi, M. Abboud, Elimination of toxic azo dye using a calcium alginate beads impregnated with NiO/activated carbon: Preparation, characterization and RSM optimization, Int J Biol Macromol 233 (2023).

DOI: 10.1016/j.ijbiomac.2023.123582

[6] N. Ali, A. Hameed, S. Ahmed, Physicochemical characterization and Bioremediation perspective of textile effluent, dyes and metals by indigenous Bacteria, J Hazard Mater 164 (2009) 322–328.

DOI: 10.1016/j.jhazmat.2008.08.006

[7] D.N. Poshina, S. V. Raik, A.N. Poshin, Y.A. Skorik, Accessibility of chitin and chitosan in enzymatic hydrolysis: A review, Polym Degrad Stab 156 (2018) 269–278.

DOI: 10.1016/j.polymdegradstab.2018.09.005

[8] P.O. Osifo, A. Webster, H. van der Merwe, H.W.J.P. Neomagus, M.A. van der Gun, D.M. Grant, The influence of the degree of cross-linking on the adsorption properties of chitosan beads, Bioresour Technol 99 (2008) 7377–7382.

DOI: 10.1016/j.biortech.2008.01.053

[9] G. Rojas, J. Silva, J.A. Flores, A. Rodriguez, M. Ly, H. Maldonado, Adsorption of chromium onto cross-linked chitosan, Sep Purif Technol 44 (2005) 31–36.

DOI: 10.1016/j.seppur.2004.11.013

[10] J. Kabuba, M. Banza, Ion-exchange process for the removal of Ni (II) and Co (II) from wastewater using modified clinoptilolite: Modeling by response surface methodology and artificial neural network, Results Eng 8 (2020).

DOI: 10.1016/j.rineng.2020.100189

[11] M. Banza, H. Rutto, T. Seodigeng, Application of Artificial Neural Network and Shrinking Core Model for Copper (Ii) and Lead (Ii) Leaching from Contaminated Soil Using Ethylenediaminetetraacetic Acid, Soil Sediment Contam (2023).

DOI: 10.1080/15320383.2023.2178384

[12] E. Igberase, P. Osifo, A. Ofomaja, Chromium (VI) ion adsorption by grafted cross-linked chitosan beads in aqueous solution–a mathematical and statistical modeling study, Environ Technol (United Kingdom) 38 (2017) 3156–3166. https://doi.org/10.1080/09593330. 2017.1290152.

DOI: 10.1080/09593330.2017.1290152

[13] C.E. Onu, J.T. Nwabanne, P.E. Ohale, C.O. Asadu, Comparative analysis of RSM, ANN and ANFIS and the mechanistic modeling in eriochrome black-T dye adsorption using modified clay, S Afr J Chem Eng 36 (2021) 24–42.

DOI: 10.1016/j.sajce.2020.12.003