Synergistic Optimization of Cd(II) Adsorption Using Modified Humic Acid: A Hybrid Response Surface Methodology-Artificial Neural Network Approach
Abstract
to predict/optimize the process. Batch experiments explored effects of pH, adsorbent dosage, initial Cd2+ concentration, and temperature;
BBD-based RSM and ANN models were built, with predictive abilities compared. RSM identified factor significance as: adsorbent dosage >
initial Cd2+ concentration > temperature > pH. The ANN model showed superior test set performance (R=0.956, RMSE=3.21) vs. traditional
RSM. HA is an efficient, low-cost heavy metal adsorbent; the RSM-ANN hybrid model effectively captured nonlinear relationships in complex adsorption systems, providing a reliable basis for optimizing heavy metal wastewater treatment.
Keywords
Full Text:
PDFReferences
[1] Ahmed, A., & Picone, J. (Eds.). (2024). Machine learning applications in medicine and biology. Springer Nature Switzerland.
[2] Bayram, O., Ozkan, U., Kardes, S., & Sahin, H. T. (2025). Machine learning-based modeling of methyl blue adsorptive removal from
aqueous solutions with lignin. Chemistryselect, 10(38).
[3] Bello, V. E., & Olafadehan, O. A. (2021). Comparative investigation of RSM and ANN for multi-response modeling and optimization
studies of derived chitosan from archachatina marginata shell. Alexandria Engineering Journal, 60(4), 38693899.
[4] Chen, H., Berndtsson, R., Ma, M., & Zhu, K. (2009). Characterization of insolubilized humic acid and its sorption behaviors. Environmental Geology, 57(8), 18471853.
[5] Ding Y., Liu M., Peng S., Li J., Liang Y., & Shi Z. (2019). Binding characteristics of heavy metals to humic acid before and after fractionation by ferrihydrite. Chemosphere, 226, 140148.
[6] Guo, X., Garcia, C., Andrade Valle, A. I., Onyelowe, K., Zarate Villacres, A. N., Ebid, A. M., & Hanandeh, S. (2024). Modeling the
influence of lime on the unconfined compressive strength of reconstituted graded soil using advanced machine learning approaches for
subgrade and liner applications. PLOS One, 19(4), e0301075.
[7] Hashem, A., Fletcher, A. J., Younis, H., Mauof, H., & Abou-Okeil, A. (2020). Adsorption of pb(II) ions from contaminated water by 1, 2, 3,
4-butanetetracarboxylic acid-modified microcrystalline cellulose: Isotherms, kinetics, and thermodynamic studies. International Journal
of Biological Macromolecules, 164, 31933203.
[8] Hokkanen, S., Bhatnagar, A., & Sillanp, M. (2016). A review on modification methods to cellulose-based adsorbents to improve adsorption capacity. Water Research, 91, 156173.
[9] Jin, C., Lu, J., Gao, Y., Hu, B., & Liu, Y. (2025). Mechanisms and optimization for simultaneous removal of cd(II) and sb(V) from aqueous solutions using birnessite and fulvic acid composite. Scientific Reports, 15(1), 19502.
[10] Kumar, P., & Tripathy, P. P. (2025). Comparative evaluation and optimization of microwave and ultrasound assisted extraction of stevia
secondary bioactive compounds using RSM and ANNGA approaches. Sustainable Food Technology.
[11] Li, H., Sun, H., Wang, J., Ma, X., & Wei, Q. (2024). Process optimization of Cd2+ removal with tetradesmus obliquus-immobilized algal beads. Biochemical Engineering Journal, 207, 109336.
[12] Manzoor, Q., Farrukh, M. A., & Sajid, A. (2024). Optimization of lead (II) and chromium (VI) adsorption using graphene oxide/ZnO/
chitosan nanocomposite by response surface methodology. Applied Surface Science, 655, 159544.
[13] Piwowarska, D., Kiedrzy?ska, E., & Jaszczyszyn, K. (2024). A global perspective on the nature and fate of heavy metals polluting water
ecosystems, and their impact and remediation. Critical Reviews in Environmental Science and Technology, 54(19), 14361458.
[14] Rathi, B. S., & Kumar, P. S. (2021). Application of adsorption process for effective removal of emerging contaminants from water and
wastewater. Environmental Pollution, 280, 116995.
DOI: http://dx.doi.org/10.70711/aitr.v3i6.8592
Refbacks
- There are currently no refbacks.
