This research examines the predictive capabilities of Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) as Machine Learning (ML) techniques for accurately modeling 10,668 data points derived from the breakthrough curves of 13 different heavy metals observed during dynamic adsorption in fixed-bed columns. Four specific models were designed and assessed: ANN1 (a one-hidden-layer ANN with logarithmic sigmoid hidden and tangent hyperbolic output activation functions); ANN2 (a two-hidden-layer ANN using logarithmic sigmoid in both hidden layers and tangent hyperbolic in the output); a conventional SVM; and an SVM-DA (SVM hybridized with the dragonfly optimization algorithm) utilizing an RBF-Gaussian kernel function. Achieving a remarkable correlation coefficient (R) of 0.9986, a root mean square error (RMSE) of 0.0209, and an average absolute relative deviation (AARD) of 24.608%, the ANN2's predicted breakthrough curves exhibited exceptional proximity to experimental observations, underscoring its robust performance in predicting dynamic adsorption phenomena. Furthermore, a sensitivity analysis employing the inverse artificial neural network method was conducted to quantify the influence of all input variables on the adsorption process. For enhanced practical utility and improved result traceability, a Graphical User Interface (GUI) was developed.
DongQLiYWeiX, et al.A city-level dataset of heavy metal emissions into the atmosphere across China from 2015–2020. Sci Data2024; 11: 1–12.
2.
AyachJEl MaltiWDumaL, et al.Comparing conventional and advanced approaches for heavy metal removal in wastewater treatment: an in-depth review emphasizing filter-based strategies. Polymers (Basel)2024; 16: 1959.
3.
HussainMKKhatoonSNizamiG, et al.Unleashing the power of bio-adsorbents: efficient heavy metal removal for sustainable water purification. J Water Process Eng2024; 64: 105705.
4.
NadakuditiAReddy-VangalaV. An overview of analytical techniques for heavy metal ion detection and removal from industrial sewage. Aibi, Rev Investig Adm e Ing2024; 12: 99–107.
5.
GahroueiAERezapourAPiroozM, et al.From classic to cutting-edge solutions: a comprehensive review of materials and methods for heavy metal removal from water environments. Desalin Water Treat2024; 319: 100446.
6.
SherazNShahAHaleemA, et al.Comprehensive assessment of carbon-, biomaterial- and inorganic-based adsorbents for the removal of the most hazardous heavy metal ions from wastewater. RSC Adv2024; 14: 11284–11310.
7.
BayuoJRwizaMJMteiKM, et al.Adsorptive Removal of Heavy Metals from Wastewater Using Low-Cost Adsorbents Derived from Agro-based Materials. Switzerland: Springer Nature, 2024.
8.
RahmanMM. Waste biomass derived chitosan-natural clay based bionanocomposites fabrication and their potential application on wastewater purification by continuous adsorption: a critical review. South Afr J Chem Eng2024; 48: 214–236.
9.
MesellemYHadjAAEl LaidiM, et al.Computational intelligence techniques for modeling of dynamic adsorption of organic pollutants on activated carbon. Neural Comput Appl2021; 33: 12493–12512.
10.
SalahshooriIWangQNobreMAL, et al.Molecular simulation-based insights into dye pollutant adsorption: A perspective review. Adv Colloid Interface Sci2024:103281. 2024.
11.
ManjunathSVSingh BaghelRKumarM. Antagonistic and synergistic analysis of antibiotic adsorption on Prosopis juliflora activated carbon in multicomponent systems. Chem Eng J2020; 381: 122713.
12.
WangJGuoX. Adsorption kinetics and isotherm models of heavy metals by various adsorbents: an overview. Crit Rev Environ Sci Technol2023; 53: 1837–1865.
13.
KrzywanskiJSosnowskiMGrabowskaK, et al.Advanced computational methods for modeling, prediction and optimization—A review. Materials (Basel)2024; 17: 3521.
14.
OlawuniOASadareOOMoothiK. The adsorption routes of 4IR technologies for effective desulphurization using cellulose nanocrystals: current trends, challenges, and future perspectives. Heliyon2024; 10: e24732.
15.
LvJWangL. Hybrid modeling of adsorption process using mass transfer and machine learning techniques for concentration prediction. J Saudi Chem Soc2025; 29: 1–12.
16.
ZafarMAggarwalAReneER, et al.Data-driven machine learning intelligent tools for predicting chromium removal in an adsorption system. Processes2022; 10: 447.
17.
MeftahSMeftahKBabassaN, et al.The versatility and effectiveness of bio-adsorbents in the removal of chemical pollutants from water: adsorption mechanisms, optimization by ANN and RSM, SWOT analysis, and contribution to the 3rd and 6 th Sustainable Development Goals. Discov Sustain2025: 971. DOI: https://doi.org/10.1007/s43621-025-01359-7.
18.
Reynel-ÁvilaHEAguayo-VillarrealIADiaz-MuñozLL, et al.A review of the modeling of adsorption of organic and inorganic pollutants from water using artificial neural networks. Adsorpt Sci Technol2022; 2022: 9384871.
19.
Gheibi M, Roohollah Masoomi S, Magala MU, et al. Environmental industry letters artificial intelligence (AI) in adsorption process of heavy metals: a systematic review. Environ Ind Lett 2024; 2: 57–78. https://journals.tultech.eu/index.php/eil.
20.
FertuDIDragoiENBulgariuL, et al.Modeling the biosorption process of heavy metal ions on neural networks. Processes2022; 10: 1–24.
21.
MichailidisPMichailidisIGkeliosS, et al.Artificial neural network applications for energy management in buildings: current trends and future directions. Energies2024; 17: 1–47.
22.
IbrahimMHaiderALimJW, et al.Artificial neural network modeling for the prediction, estimation, and treatment of diverse wastewaters: a comprehensive review and future perspective. Chemosphere2024; 142860: 142860.
23.
PanSDuraisamyK. Long-time predictive modeling of nonlinear dynamical systems using neural networks. Complexity2018; 2018: 4801012.
24.
AlatawiMNAlyahyanSHussainS, et al.A data-driven artificial neural network approach to software project risk assessment. IET Softw2023; 2023: 1–19.
25.
KhaouaneLBenkortbiOHaniniS, et al.Modeling of an industrial process of pleuromutilin fermentation using feed-forward neural networks. Brazilian J Chem Eng2013; 30: 105–116.
26.
GhaediAMVafaeiA. Applications of artificial neural networks for adsorption removal of dyes from aqueous solution: a review. Adv Colloid Interface Sci2017; 245: 20–39.
27.
MaW. Power system shortterm load forecasting based on improved support vector machines. In: Proc - 2008 Int Symp Knowl Acquis Model KAM, 2008, p. 658–662. 10.1109/KAM.2008.68
28.
MoumenRLaidiMHaniniS, et al.Multicomponent adsorption capacity forecasting based on support vector machine with dragonfly algorithm. Kem u Ind2023; 72: 3–4.
29.
FengYZhangPYangM, et al.Short term load forecasting of offshore oil field microgrids based on DA-SVM. Energy Procedia2019; 158: 2448–2455.
30.
MengFZouQZhangZ, et al.An intelligent hybrid wavelet-adversarial deep model for accurate prediction of solar power generation. Energy Reports2021; 7: 2155–2164.
31.
JasimRNAl-QaraghuliASNasarZA. Exploring the intersection of biological and artificial neural networks in architectural contexts, followed by investigation of algorithms supporting the evolution of the design process. BIO Web Conf2024; 97: 1–11.
32.
Agatonovic-KustrinSBeresfordR. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed Anal2000; 22: 717–727.
33.
RezraziAHaniniSLaidiM. An optimisation methodology of artificial neural network models for predicting solar radiation: a case study. Theor Appl Climatol2016; 123: 769–783.
34.
RigolJPJarvisCHStuartN. Artificial neural networks as a tool for spatial interpolation. Int J Geogr Inf Sci2001; 15: 323–343.
35.
BossartJ. Opening the black box. Pharm Manuf Pack Sourcer2010; 16: 32–34.
36.
AbrahamA. Adaptation of fuzzy inference system using neural learning. Berlin, Heidelberg: Springer, 2005.
37.
Si-MoussaCHaniniSDerricheR, et al.Prediction of high-pressure vapor liquid equilibrium of six binary systems, carbon dioxide with six esters, using an artificial neural network model. Brazilian J Chem Eng2008; 25: 183–199.
GhaddarBNaoum-SawayaJ. High dimensional data classification and feature selection using support vector machines. Eur J Oper Res2018; 265: 993–1004.
40.
BafitlhileTMLiZ. Applicability of ε-Support Vector Machine and artificial neural network for flood forecasting in humid, semi-humid and semi-arid basins in China. Water (Switzerland)2019; 11: 85.
41.
LiM. Generalized Lagrange multiplier method and KKT conditions with an application to distributed optimization. IEEE Trans Circuits Syst II Express Briefs2019; 66: 252–256.
42.
MeraihiYRamdane-CherifAAcheliD, et al.Dragonfly algorithm: a comprehensive review and applications. Neural Comput Appl2020; 32: 16625–16646.
43.
MirjaliliS. Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Comput Appl2016; 27: 1053–1073.
44.
ReynoldsCW. Flocks, herds, and schools: a distributed behavioral model. In: Proc 14th Annu Conf Comput Graph Interact Tech SIGGRAPH, 1987; 21: p. 25–34. 10.1145/37401.37406
45.
BenimamHMoussaCSHentabliM, et al.Dragonfly-Support vector machine for regression modeling of the activity coefficient at infinite dilution of solutes in imidazolium ionic liquids using σ-profile descriptors. J Chem Eng Data2020; 65: 3161–3172.
46.
ZhuHHuangQShiM, et al.Adsorption of Sb(III) from aqueous solution by nzvi/ac: a magnetic fixed-bed column study. Nanomaterials2021; 11: 1–11.
47.
ZhuDHeYZhangB, et al.Simultaneous removal of multiple heavy metals from wastewater by novel plateau laterite ceramic in batch and fixed-bed studies. J Environ Chem Eng2021; 9: 105792.
48.
AbdolaliANgoHHGuoW, et al.Application of a breakthrough biosorbent for removing heavy metals from synthetic and real wastewaters in a lab-scale continuous fixed-bed column. Bioresour Technol2017; 229: 78–87.
49.
KhalfaLSdiriABaganeM, et al.A calcined clay fixed bed adsorption studies for the removal of heavy metals from aqueous solutions. J Clean Prod2021; 278: 123935.
50.
SatyaAHarimawanASri HaryaniG, et al.Fixed-bed adsorption performance and empirical modelingof cadmium removal using adsorbent prepared from the cyanobacterium aphanothece sp cultivar. Environ Technol Innov2021; 21: 101194.
51.
PatelH. Batch and continuous fixed bed adsorption of heavy metals removal using activated charcoal from neem (azadirachta indica) leaf powder. Sci Rep2020; 10: 1–12.
52.
RindIKMemonNKhuhawarMY, et al.Modeling of cadmium(II) removal in a fixed bed column utilizing hydrochar-derived activated carbon obtained from discarded mango peels. Sci Rep2022; 12: 1–15.
53.
SrivastavaSAgrawalSBMondalMK. Fixed bed column adsorption of Cr(VI) from aqueous solution using nanosorbents derived from magnetite impregnated Phaseolus vulgaris husk. Environ Prog Sustain Energy2019; 38: S68–S76.
54.
YükselŞOrhanR. The removal of Cr(VI) from aqueous solution by activated carbon prepared from apricot, peach stone and almond shell mixture in a fixed-bed column. Arab J Sci Eng2019; 44: 5345–5357.
55.
KumarSPatraCNarayanasamyS, et al.Performance of acid-activated water caltrop (Trapa natans) shell in fixed bed column for hexavalent chromium removal from simulated wastewater. Environ Sci Pollut Res2020; 27: 28042–28052.
56.
KebirMTahraouiHChabaniM, et al.Water cleaning by a continuous fixed-bed column for Cr(VI) eco-adsorption with green adsorbent-based biomass: an experimental modeling study. Processes2023; 11: 363.
57.
YusufMSongK. Removal of Co(II) and Cr(III) from aqueous solution by graphene nanosheet/δ-MnO2: batch and column studies. Chem Eng Res Des2020; 159: 477–490.
58.
EgbosiubaTCAbdulkareemAS. Highly efficient as-synthesized and oxidized multi-walled carbon nanotubes for copper(II) and zinc(II) ion adsorption in a batch and fixed-bed process. J Mater Res Technol2021; 15: 2848–2872.
59.
Mve MfoumouCTonda-MikiélaPNgoyeF, et al.Removal and adsorption kinetics of copper(II) ions from aqueous media on activated carbon in dynamic adsorption on a fixed-bed column. Comptes Rendus Chim2024; 27: 141–151.
60.
FallahNTaghizadehM. Continuous fixed-bed adsorption of Mo(VI) from aqueous solutions by Mo(VI)-IIP: breakthrough curves analysis and mathematical modeling. J Environ Chem Eng2020; 8: 104079.
61.
MaddodiSAAlalwanHAAlminshidAH, et al.Isotherm and computational fluid dynamics analysis of nickel ion adsorption from aqueous solution using activated carbon. South African J Chem Eng2020; 32: 5–12.
62.
RindIKMemonNKhuhawarMY, et al.Thermally activated mango peels hydrochar for fixed-bed continuous flow decontamination of Pb(II) ions from aqueous solution. Int J Environ Sci Technol2022; 19: 2835–2850.
63.
LakshmipathyRBalajiGLRicoILR. Removal of Pb2+ions by ZSM-5/AC composite in a fixed-bed bench scale system. Adsorpt Sci Technol2021; 2021: 2013259.
64.
VanceaCMihailescuMNegreaA, et al.Batch and fixed-bed column studies on palladium recovery from acidic solution by modified mgsio3. Int J Environ Res Public Health2020; 17: 1–17.
65.
MoraBPBertoniFAMangiameliMF, et al.Batch and fixed-bed column studies of selenite removal from contaminated water by orange peel-based sorbent. Water Sci Eng2020; 13: 307–316.
66.
ShanmugaprakashMSivakumarV. Batch and fixed-bed column studies for biosorption of Zn(II) ions onto pongamia oil cake (Pongamia pinnata) from biodiesel oil extraction. J Environ Manage2015; 164: 161–170.
67.
SoleimaniRSaeedi DehaghaniAHShoushtariNA, et al.Toward an intelligent approach for predicting surface tension of binary mixtures containing ionic liquids. Korean J Chem Eng2018; 35: 1556–1569.
68.
RossT. Indices for performance evaluation of predictive models in food microbiology. J Appl Bacteriol1996; 81: 501–508.
