Prediction of Dye Removal Using Machine Learning Techniques

Abstract

This study aims to predict the removal efficiency of methylene blue dye using experimental data collected from adsorption processes involving acorn-based biosorbents. A comparative evaluation of four machine learning algorithms (Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), Random Forest, and XGBoost) was conducted to determine the most suitable modeling approach. Two ANN architectures, with single and dual hidden layers respectively, achieved the highest predictive accuracy, with R² values of 0.93 and 0.87. While XGBoost demonstrated better performance (R² = 0.64) than Random Forest (R² = 0.61), both ensemble models provided moderately accurate predictions. In contrast, the LSTM model performed poorly (R² = 0.44), likely due to the non-sequential structure of the dataset. These findings underscore the potential of ANN-based models for accurately capturing nonlinear relationships in adsorption systems and also demonstrate the viability of alternative ensemble learning methods for predictive environmental modeling.

Keywords

• Adsorption modeling
• Artificial Neural Networks
• XGBoost
• LSTM
• Dye removal
• Predictive modeling

References

1. A. Asfaram et al., “Preparation and characterization of Mn0. 4Zn0. 6Fe2O4 nanoparticles supported on dead cells of Yarrowia lipolytica as a novel and efficient adsorbent/biosorbent composite for the removal of azo food dyes: central composite design optimization study,” ACS Sustainable Chem. Eng., vol. 6, no. 4, pp. 4549-4563, 2018.
2. M.R. Gadekar and M.M. Ahammed, “Modelling dye removal by adsorption onto water treatment residuals using combined response surface methodology-artificial neural network approach”, J. Environ. Manag., vol. 231, pp. 241–248, 2019..
3. A.S. Al-Wasidi, F.A. Saad, S. AlReshaidan and A.M. Naglah, “Facile Synthesis of ZSM-5/TiO2/Ni Novel Nanocomposite for the Efficient Photocatalytic Degradation of Methylene Blue Dye”, J. Inorg. Organomet. Polym. Mat., vol. 32, pp. 3040–3052, 2022.
4. S. Vajnhandl and J.V. Valh, “The status of water reuse in European textile sector”, J. Environ. Manage., vol. 141, pp. 29-35, 2014.
5. M. F. Pinheiro, G.S. Rodrigues, J.A. Junior, R. de Sousa, and de A.R. da Costa, "Analysis of the adsorptive capacity of arabic coffee straw using blue methylene dye", Braz. J. Dev., vol. 6, no. 1, pp. 2861-2868, 2020.
6. A. Arı, ve M.E. Berberler, "Yapay Sinir Ağları ile Tahmin ve Sınıflandırma Problemlerinin Çözümü İçin Arayüz Tasarımı", Acta Infologica, vol.1, no.2, pp. 55-75, 2017.
7. H. Esen, "Düşey borulu toprak kaynaklı ısı pompasının konutlardaki iklimlendirme sistemlerinde mevsimsel davranışın araştırılması", Doktora Tezi, Fırat Üniversitesi, Fen Bilimleri Enstitüsü, Elazığ 2007.
8. T. Partal, "Türkiye yağış miktarının yapay sinir ağları ve dalgacık dönüşümü yöntemleri ile tahmini", Doktora Tezi, İstanbul Teknik Üniversitesi, Fen Bilimleri Enstitüsü, İstanbul, 2007.

9. N. G. Polsona, and V.O. Sokolov, “Deep learning for short-term traffic flow prediction, Transportation Research Part C:” Emerging Technologies, vol.79, pp.1-17, 2017
10. A. Kardam, K.R. Raj, J. K. Arora and S. Srivastava, “Simulation and Optimization of Artificial Neural Network Modeling for Prediction of Sorption Efficiency of Nanocellulose Fibers for Removal of Cd (II) Ions from Aqueous System”, Eng. Phys. Sci., vol. 11, no. 6, pp. 497‐508, 2014.
11. N. Donut, and L. Cavas, “Artificial Neural Network Modeling of Tetracycline Biosorption by Pre-treated Posidonia oceanica”, Turkish J. Fish. Aquat. Sc., vol.17, pp. 1317-1333, 2017.
12. A.A. Amouei, F. Amooey and F. Asgharzadeh, “A study of cadmium removal from aqueous solutions by sunflower powders and its modeling using artificial neural network”, Iran. J. Health Sci., vol. 1, no.3, pp. 28-34, 2013.
13. S. M. El-Said et al., “Adsorptive removal of Arsenite as (III) and Arsenate as (V) heavy metals from wastewater using Nigella sativa L.”, J. Asian Sci. Res., vol. 2, pp. 96-104, 2009.
14. M. Garza-González et al., “Artificial neural network for predicting biosorption of methylene blue by Spirulina sp.”, Water Sci. Technol., vol. 75, no.5, pp. 977-983, 2011.
15. S. E. Çoruh, E. Kılıç and F. Geyikci, “Prediction of adsorption efficiency for the removal of malachite green and acid blue 161 dyes by waste marble dust using ANN”, Global Nest J., vol. 16, no.4, pp. 676-689, 2014.
16. N. Öztürk, H.B. Şentürk, A. Gündoğdu and C. Duran, “İçme suyu arıtma tesisi atık çamuru üzerine metilen mavisi adsorpsiyonu ve yapay sinir ağları ile modellenmesi”, Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, vol. 25, no. 2, pp. 1083-1103, 2020.
17. Barna, S. D., Jahan, M. N., Sium, S. R., Nag, A., Ali, M. H., & Dutta, S. K. (2024). Sustainable cost-effective chemically modified banana leaf powder for methyl blue dye removal: kinetics, isotherm, thermodynamics and artificial intelligence-based analysis. Discover Chemistry, 1(1), 38.
18. Kalsoom, Ali, A., Khan, S., Ali, N., & Khan, M. A. (2024). Enhanced ultrasonic adsorption of pesticides onto the optimized surface area of activated carbon and biochar: adsorption isotherm, kinetics, and thermodynamics. Biomass Conversion and Biorefinery, vol. 14, no. 14, pp. 15519-15534.
19. Ganthavee, V., Fernando, M. M., & Trzcinski, A. P. (2024). Monte carlo simulation, artificial intelligence and machine learning-based modelling and optimization of three-dimensional electrochemical treatment of Xenobiotic Dye wastewater. Environmental Processes, vol. 11, no. 3, p. 41.
20. Bahrami, M., Amiri, M. J., Rajabi, S., & Mahmoudi, M. (2024). The removal of methylene blue from aqueous solutions by polyethylene microplastics: Modeling batch adsorption using random forest regression. Alexandria Engineering Journal, 95, pp. 101-113.
21. Yaseen, Z. M., & Alhalimi, F. L. (2025). Heavy metal adsorption efficiency prediction using biochar properties: a comparative analysis for ensemble machine learning models. Scientific Reports, vol. 15, no. 1, p. 13434.