Comparative Study of Machine Learning Algorithms for Cr(VI) Adsorption Optimization: A Case Study Using KOH-Activated Wood Charcoal

Moh. Azhar Afandy, Fikrah Dian Indrawati Sawali

Abstract

The removal of toxic Cr(VI) ions from industrial wastewater remains a pressing environmental concern due to their high mobility and carcinogenic nature. This study presents a data-driven approach for modeling and optimizing Cr(VI) adsorption onto KOH-activated wood charcoal using various machine learning (ML) algorithms. A dataset derived from batch adsorption experiments was used, involving three operational parameters: initial Cr(VI) concentration (10–50 mg/L), contact time (40–120 min), and adsorbent dose (0.5–1.5 g). Six supervised regression models such as Linear Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), Gradient Boosting, and k-Nearest Neighbors (kNN) were evaluated. Model performance was assessed using the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) dan mean square error (MSE). Gradient Boosting and Decision Tree showed superior predictive accuracy, with R² values of 0.89 and 0.87, respectively. Feature importance analysis revealed initial concentration as the most influential factor, followed by contact time and adsorbent dosage. These findings highlight the potential of ML as an effective tool for predicting and optimizing adsorption processes in environmental remediation. The integration of ML methods supports efficient decision-making, particularly under constraints of limited experimental data, and aligns with digital transformation strategies in wastewater treatment.

Full Text:

PDF

References

Ş. Parlayici and E. Pehlivan, “Comparative study of Cr(VI) removal by bio-waste adsorbents: equilibrium, kinetics, and thermodynamic,” J. Anal. Sci. Technol., vol. 10, no. 1, 2019,

L. Cervera-Gabalda and C. Gómez-Polo, “Magnetic Fe/Fe3C@C Nanoadsorbents for Efficient Cr (VI) Removal,” 2022.

M. N. Georgaki et al., “Chromium in Water and Carcinogenic Human Health Risk,” Environ. - MDPI, vol. 10, no. 2, pp. 1–26, 2023,

M. N. Georgaki and M. Charalambous, “Toxic chromium in water and the effects on the human body: a systematic review,” J. Water Health, vol. 21, no. 2, pp. 205–223, 2023,

A. Zhitkovich, “Chromium in drinking water: Sources, metabolism, and cancer risks,” Chem. Res. Toxicol., vol. 24, no. 10, pp. 1617–1629, 2011,

P. P. Prabhu and B. Prabhu, “A Review on Removal of Heavy Metal Ions from Waste Water using Natural/ Modified Bentonite,” MATEC Web Conf., vol. 144, pp. 1–13, 2018,

N. Khatri, S. Tyagi, and D. Rawtani, “Recent strategies for the removal of iron from water: A review,” J. Water Process Eng., vol. 19, no. 13, pp. 291–304, 2017,

J. O. Ighalo, S. Budi, K. O. Iwuozor, C. O. Aniagor, O. J. Ajala, and S. N. Oba, “A review of treatment technologies for the mitigation of the toxic environmental effects of acid mine drainage (AMD),” Process Saf. Environ. Prot., vol. 157, pp. 37–58, 2022,

E. Windiastuti, N. S. Indrasti, U. Hasanudin, Y. Bindar, and Suprihatin, “The Influence of Pretreatment and Post Treatment with Alkaline Activators on the Adsorption Ability of Biochar from Palm Oil Empty Fruit,” J. Ecol. Eng., vol. 24, no. 10, pp. 242–251, 2023,

C. Liu et al., “Preparation of Acid- and Alkali-Modified Biochar for Removal of Methylene Blue Pigment,” ACS Omega, vol. 5, no. 48, pp. 30906–30922, Dec. 2020,

M. R. R. Kooh, R. Thotagamuge, Y.-F. Chou Chau, A. H. Mahadi, and C. M. Lim, “Machine learning approaches to predict adsorption capacity of Azolla pinnata in the removal of methylene blue,” J. Taiwan Inst. Chem. Eng., vol. 132, p. 104134, 2022,

T. Zarei, M. Chatavi, M. Nazari, A. Amirfakhraei, M. Amidpour, and M. Salimi, “Machine Learning-Based Model Prediction of an Adsorption Desalination System and Investigation of the Impact of Parameters on the System’s Outputs,” 2024, [Online]. Available: https://papers.ssrn.com/abstract=4608483

R. Ahmad Aftab et al., “Removal of congo red from water by adsorption onto activated carbon derived from waste black cardamom peels and machine learning modeling,” Alexandria Eng. J., vol. 71, pp. 355–369, 2023,

Z. Wang, Q. Wang, F. Yang, C. Wang, M. Yang, and J. Yu, “How machine learning boosts the understanding of organic pollutant adsorption on carbonaceous materials: A comprehensive review with statistical insights,” Sep. Purif. Technol., vol. 350, p. 127790, 2024,

Z. Haider Jaffari et al., “Machine-learning-based prediction and optimization of emerging contaminants’ adsorption capacity on biochar materials,” Chem. Eng. J., vol. 466, p. 143073, 2023,

L. R. Oviedo, V. R. Oviedo, L. D. Dalla Nora, and W. L. da Silva, “Adsorption of organic dyes onto nanozeolites: A machine learning study,” Sep. Purif. Technol., vol. 315, p. 123712, 2023,

K. F. S. Richard, D. C. S. Azevedo, and M. Bastos-Neto, “Investigation and Improvement of Machine Learning Models Applied to the Optimization of Gas Adsorption Processes,” Ind. Eng. Chem. Res., vol. 62, no. 18, pp. 7093–7102, May 2023,

M. A. Afandy and F. D. I. Sawali, “Comprehensive Study on Cr ( VI ) Adsorption and Regeneration Behavior of Alkali-Treated Wood Charcoal : Isotherms and Kinetics Models,” IPTEK, J. Eng., vol. 11, no. 2, pp. 1–17, 2025.

D. Miller and J. M. Kim, “Univariate and Multivariate Machine Learning Forecasting Models on the Price Returns of Cryptocurrencies,” J. Risk Financ. Manag., vol. 14, no. 10, 2021,

G. Hesamian and M. G. Akbari, “Fuzzy spline univariate regression with exact predictors and fuzzy responses,” J. Comput. Appl. Math., vol. 375, p. 112803, 2020,

D. Ramadhani, A. M. Soleh, and Erfiani, “Machine Learning-Based Univariate Time Series Imputation Method for Estimating Missing Values in Non- Stationary Data,” J. Mat. Stat. dan Komputasi, vol. 21, no. 1, pp. 307–320, 2024,

M. R. Skonja and Igor Kononenko, “Theoretical and Empirical Analysis of ReliefF and RReliefF,” Mach. Learn., vol. 53, pp. 23–69, 2003, [Online]. Available: http://lkm.fri.uni-lj.si/xaigor/slo/clanki/MLJ2003-FinalPaper.pdf

A. Elbeltagi, S. Heddam, O. M. Katipoğlu, A. A. Alsumaiei, and M. Al-Mukhtar, “Advanced long-term actual evapotranspiration estimation in humid climates for 1958–2021 based on machine learning models enhanced by the RReliefF algorithm,” J. Hydrol. Reg. Stud., vol. 56, 2024,

R. J. Urbanowicz, M. Meeker, W. La Cava, R. S. Olson, and J. H. Moore, “Relief-based feature selection: Introduction and review,” J. Biomed. Inform., vol. 85, no. July, pp. 189–203, 2018,

T. C. Phan, A. Pranata, J. Farragher, A. Bryant, H. T. Nguyen, and R. Chai, “Regression-Based Machine Learning for Predicting Lifting Movement Pattern Change in People with Low Back Pain,” Sensors, vol. 24, no. 4, 2024,

P. S. Kumar, L. Korving, M. C. M. van Loosdrecht, and G. J. Witkamp, “Adsorption as a technology to achieve ultra-low concentrations of phosphate: Research gaps and economic analysis,” Water Res. X, vol. 4, p. 100029, 2019,

D. Dermawan et al., “Composite adsorbent from sugarcane (Saccharum officinarum) bagasse biochar generated from atmospheric pressure microwave plasma pyrolysis process and nano zero valent iron (nZVI) for rapid and highly efficient Cr(VI) adsorption,” Case Stud. Chem. Environ. Eng., vol. 11, no. November 2024, 2025,

S. Panić et al., “Optimization of thiamethoxam adsorption parameters using multi-walled carbon nanotubes by means of fractional factorial design,” Chemosphere, vol. 141, pp. 87–93, 2015,

DOI: https://doi.org/10.20961/equilibrium.v10i1.108769

Refbacks

  • There are currently no refbacks.