Abstract
The removal of reactive red M-2BE dye textile from aqueous solution was performed using multi-walled carbon nanotubes (MWCN) and powdered activated carbon (PAC). Kinetic adsorption modeling has been performed using machine learning (ML) algorithms of artificial neural networks, adaptive-neuro fuzzy inference system (ANFIS), random forest, gradient boosting, and support vector machine. Although ML models are more accurate, they often fail to interpret the reasoning behind predictions. Therefore, the SHapley Additive exPlanations (SHAP) were used to understand the effect of each feature on the adsorption capacity. The ANFIS has presented the best statistical metrics with \(R=0.9993\), \(RMSE=0.0214\), and \(SAE=7.1172\). A higher adsorption capacity was observed for MWCN compared to PAC; while the first peaked at 300 mg L−1, the second approached 230 mg L−1. Temperature was found to have the smallest contribution in describing adsorption capacity. This novel application of ML with SHAP can provide important insights for adsorption researchers.
Similar content being viewed by others
Availability of data and materials
Data will be made available on request.
References
Aria, M., Cuccurullo, C., Gnasso, A.: A comparison among interpretative proposals for random forests. Mach. Learn. Appl. 6, 100094 (2021). https://doi.org/10.1016/j.mlwa.2021.100094
Assad, H., Fatma, I., Kumar, A., Kaya, S., Vo, D.-V.N., Al-Gheethi, A., Sharma, A.: An overview of MXene-Based nanomaterials and their potential applications towards hazardous pollutant adsorption. Chemosphere 298, 134221 (2022). https://doi.org/10.1016/j.chemosphere.2022.134221
Nogueira, I.B.R., Santana, V., Ribeiro, V., Ribeiro, A.M., Rodrigues, A.E.: Using scientific machine learning to develop universal differential equation for multicomponent adsorption separation systems. Can. J. Chem. Eng. 100, 2279–2290 (2022). https://doi.org/10.1002/cjce.24495
Bierdel, M., Buchholz, S., Michele, V., Mleczko, L., Rudolf, R., Voetz, M., Wolf, A.: Industrial production of multiwalled carbon nanotubes. Phys. Stat. Sol. 244, 3939–3943 (2007). https://doi.org/10.1002/pssb.200776101
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001). https://doi.org/10.1023/A:1010933404324
Cai, W., Wei, R., Xu, L., Ding, X.: A method for modelling greenhouse temperature using gradient boost decision tree. Inf. Process. Agric. 9, 343–354 (2022). https://doi.org/10.1016/j.inpa.2021.08.004
Cervantes, J., Garcia-Lamont, F., Rodríguez-Mazahua, L., Lopez, A.: A comprehensive survey on support vector machine classification: applications, challenges and trends. Neurocomputing 408, 189–215 (2020). https://doi.org/10.1016/j.neucom.2019.10.118
Chopra, S., Dhiman, G., Sharma, A., Shabaz, M., Shukla, P., Arora, M.: Taxonomy of adaptive neuro-fuzzy inference system in modern engineering sciences. Comput. Intell. Neurosci. 2021, 1–14 (2021). https://doi.org/10.1155/2021/6455592
Cristianini, N., Shawe-Taylor, J.: An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge (2000)
Diehl, M., Silva, L.F.O., Schnorr, C., Netto, M.S., Bruckmann, F.S., Dotto, G.L.: Cassava bagasse as an alternative biosorbent to uptake methylene blue environmental pollutant from water. Environ. Sci. Pollut. Res. 30, 51920–51931 (2023). https://doi.org/10.1007/s11356-023-26006-4
Dil, E.A., Ghaedi, M., Ghezelbash, G.R., Asfaram, A., Ghaedi, A.M., Mehrabi, F.: Modeling and optimization of Hg 2+ ion biosorption by live yeast Yarrowia lipolytica 70562 from aqueous solutions under artificial neural network-genetic algorithm and response surface methodology: kinetic and equilibrium study. RSC Adv. 6, 54149–54161 (2016). https://doi.org/10.1039/C6RA11292G
Dolatabadi, M., Mehrabpour, M., Esfandyari, M., Alidadi, H., Davoudi, M.: Modeling of simultaneous adsorption of dye and metal ion by sawdust from aqueous solution using of ANN and ANFIS. Chemom. Intell. Lab. Syst. 181, 72–78 (2018). https://doi.org/10.1016/j.chemolab.2018.07.012
Dong, M., Guo, J., Wang, Y., Gai, X., Xiong, X., Zeng, J., Wang, Y., Wu, Y.: Humic acid non-covalent functionalized multi-walled carbon nanotubes composite membrane and its application for the removal of organic dyes. J. Environ. Chem. Eng. 10, 107320 (2022). https://doi.org/10.1016/j.jece.2022.107320
Ekanayake, I.U., Meddage, D.P.P., Rathnayake, U.: A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Stud. Constr. Mater. 16, e01059 (2022). https://doi.org/10.1016/j.cscm.2022.e01059
Fan, M., Hu, J., Cao, R., Ruan, W., Wei, X.: A review on experimental design for pollutants removal in water treatment with the aid of artificial intelligence. Chemosphere 200, 330–343 (2018). https://doi.org/10.1016/j.chemosphere.2018.02.111
Gasparetto, H., de Castilhos, F., Salau, N.P.G.: Unveiling the generalization of the derivative order with a novel application of the fractional order model to green soybean oil extraction. Chem. Eng. Res. Design (2023). https://doi.org/10.1016/j.cherd.2023.02.038
Gasparetto, H., de Castilhos, F., Salau, N.P.G.: Screening, experimental data, and robust kinetic modeling of vegetable oil extraction using p-cymene as a neoteric solvent for n-hexane replacement. J. Clean. Prod. 392, 136336 (2023). https://doi.org/10.1016/j.jclepro.2023.136336
Gasparetto, H., Nunes, A.L.B., de Castilhos, F., Salau, N.P.G.: Soybean oil extraction using ethyl acetate and 1-butanol: from solvent selection to thermodynamic assessment. J. Ind. Eng. Chem. 113, 450–460 (2022). https://doi.org/10.1016/j.jiec.2022.06.020
Genuer, R., Poggi, J.-M.: Random forests with R. Springer International Publishing, Cham (2020)
Hafsa, N., Rushd, S., Al-Yaari, M., Rahman, M.: A generalized method for modeling the adsorption of heavy metals with machine learning algorithms. Water 12, 3490 (2020). https://doi.org/10.3390/w12123490
Harja, M., Buema, G., Bucur, D.: Recent advances in removal of Congo Red dye by adsorption using an industrial waste. Sci. Rep. 12, 6087 (2022). https://doi.org/10.1038/s41598-022-10093-3
James, G., Witten, D., Hastie, T., Tibshirani, R.: An introduction to statistical learning. Springer, New York (2013)
Kanjal, M.I., Muneer, M., Jamal, M.A., Bokhari, T.H., Wahid, A., Ullah, S., Amrane, A., Hadadi, A., Tahraoui, H., Mouni, L.: A study of treatment of reactive red 45 dye by advanced oxidation processes and toxicity evaluation using bioassays. Sustainability. 15, 7256 (2023). https://doi.org/10.3390/su15097256
Khan, F.S.A., Mubarak, N.M., Tan, Y.H., Khalid, M., Karri, R.R., Walvekar, R., Abdullah, E.C., Nizamuddin, S., Mazari, S.A.: A comprehensive review on magnetic carbon nanotubes and carbon nanotube-based buckypaper for removal of heavy metals and dyes. J. Hazard. Mater. 413, 125375 (2021). https://doi.org/10.1016/j.jhazmat.2021.125375
Kim, Y.-W., Kim, J.-H., Moon, D.H., Shin, H.-J.: Adsorption and precipitation of anionic dye Reactive Red 120 from aqueous solution by aminopropyl functionalized magnesium phyllosilicate. Korean J. Chem. Eng. 36, 101–108 (2019). https://doi.org/10.1007/s11814-018-0168-8
Lawrence, R.: Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis. Remote Sens. Environ. 90, 331–336 (2004). https://doi.org/10.1016/j.rse.2004.01.007
Li, Z., Sellaoui, L., Dotto, G.L., Lamine, A.B., Bonilla-Petriciolet, A., Hanafy, H., Belmabrouk, H., Netto, M.S., Erto, A.: Interpretation of the adsorption mechanism of Reactive Black 5 and Ponceau 4R dyes on chitosan/polyamide nanofibers via advanced statistical physics model. J. Mol. Liq. 285, 165–170 (2019). https://doi.org/10.1016/j.molliq.2019.04.091
Machado, F.M., Bergmann, C.P., Fernandes, T.H.M., Lima, E.C., Royer, B., Calvete, T., Fagan, S.B.: Adsorption of Reactive Red M-2BE dye from water solutions by multi-walled carbon nanotubes and activated carbon. J. Hazard. Mater. 192, 1122–1131 (2011). https://doi.org/10.1016/j.jhazmat.2011.06.020
Maulana Kusdhany, M.I., Lyth, S.M.: New insights into hydrogen uptake on porous carbon materials via explainable machine learning. Carbon 179, 190–201 (2021). https://doi.org/10.1016/j.carbon.2021.04.036
McDonald, G., García-Pedrajas, N., Macdonald, C., Ounis, I.: A Study of SVM kernel functions for sensitivity classification ensembles with POS sequences. In: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval. pp. 1097–1100. ACM, Shinjuku Tokyo Japan (2017)
Nascimento, V.X., Pinto, D., Lütke, S.F., Da Silva, M.C.F., Machado, F.M., Lima, É.C., Silva, L.F.O., Dotto, G.L.: Brilliant blue FCF dye adsorption using magnetic activated carbon from Sapelli wood sawdust. Environ. Sci. Pollut. Res. 30, 58684–58696 (2023). https://doi.org/10.1007/s11356-023-26646-6
Netto, M.S., Oliveira, J.S., Salau, N.P.G., Dotto, G.L.: Analysis of adsorption isotherms of Ag+, Co+2, and Cu+2 onto zeolites using computational intelligence models. J. Environ. Chem. Eng. 9, 104960 (2021). https://doi.org/10.1016/j.jece.2020.104960
Oliveira, L.M.C., Dias, R., Rebello, C.M., Martins, M.A.F., Rodrigues, A.E., Ribeiro, A.M., Nogueira, I.B.R.: Artificial intelligence and cyber-physical systems: a review and perspectives for the future in the chemical industry. AI 2, 429–443 (2021). https://doi.org/10.3390/ai2030027
Onsree, T., Tippayawong, N., Phithakkitnukoon, S., Lauterbach, J.: Interpretable machine-learning model with a collaborative game approach to predict yields and higher heating value of torrefied biomass. Energy 249, 123676 (2022). https://doi.org/10.1016/j.energy.2022.123676
Pang, X., Sellaoui, L., Franco, D., Dotto, G.L., Georgin, J., Bajahzar, A., Belmabrouk, H., Ben Lamine, A., Bonilla-Petriciolet, A., Li, Z.: Adsorption of crystal violet on biomasses from pecan nutshell, para chestnut husk, araucaria bark and palm cactus: experimental study and theoretical modeling via monolayer and double layer statistical physics models. Chem. Eng. J. 378, 122101 (2019). https://doi.org/10.1016/j.cej.2019.122101
Pauletto, P.S., Gonçalves, J.O., Pinto, L.A.A., Dotto, G.L., Salau, N.P.G.: Single and competitive dye adsorption onto chitosan–based hybrid hydrogels using artificial neural network modeling. J. Colloid Interface Sci. 560, 722–729 (2020). https://doi.org/10.1016/j.jcis.2019.10.106
Pauletto, P.S., Lütke, S.F., Dotto, G.L., Salau, N.P.G.: Forecasting the multicomponent adsorption of nimesulide and paracetamol through artificial neural network. Chem. Eng. J. 412, 127527 (2021). https://doi.org/10.1016/j.cej.2020.127527
Piazzi Fuhr, A.C.F., Vieira, Y., Kuhn, R.C., Salau, N.P.G.: Selective adsorption processes for fructooligosaccharides separation by activated carbon and zeolites through machine learning. Chem. Eng. Res. Design 190, 379–394 (2023). https://doi.org/10.1016/j.cherd.2022.12.041
Rápó, E., Tonk, S.: Factors affecting synthetic dye adsorption; desorption studies: a review of results from the last five years (2017–2021). Molecules 26, 5419 (2021). https://doi.org/10.3390/molecules26175419
Ravindiran, G., Saravanan, P., Alagumalai, A., Subbarayan, S.: Soft computing-based models and decolorization of Reactive Yellow 81 using Ulva Prolifera biochar. Chemosphere 287, 132368 (2022). https://doi.org/10.1016/j.chemosphere.2021.132368
Rebello, C.M., Marrocos, P.H., Costa, E.A., Santana, V.V., Rodrigues, A.E., Ribeiro, A.M., Nogueira, I.B.R.: Machine learning-based dynamic modeling for process engineering applications: a guideline for simulation and prediction from perceptron to deep learning. Processes 10, 250 (2022). https://doi.org/10.3390/pr10020250
Rego, A.S.C., Valim, I.C., Vieira, A.A.S., Vilani, C., Santos, B.F.: Optimization of sugarcane bagasse pretreatment using alkaline hydrogen peroxide through ANN and ANFIS modelling. Biores. Technol. 267, 634–641 (2018). https://doi.org/10.1016/j.biortech.2018.07.087
Rodrigues, F.K., Salau, N.P.G., Dotto, G.L.: New insights about reactive red 141 adsorption onto multi–walled carbon nanotubes using statistical physics coupled with Van der Waals equation. Sep. Purif. Technol. 224, 290–294 (2019). https://doi.org/10.1016/j.seppur.2019.05.042
Sellaoui, L., Dotto, G.L., Peres, E.C., Benguerba, Y., Lima, É.C., Lamine, A.B., Erto, A.: New insights into the adsorption of crystal violet dye on functionalized multi-walled carbon nanotubes: experiments, statistical physics and COSMO–RS models application. J. Mol. Liq. 248, 890–897 (2017). https://doi.org/10.1016/j.molliq.2017.10.124
Souza, P.R., Dotto, G.L., Salau, N.P.G.: Artificial neural network (ANN) and adaptive neuro-fuzzy interference system (ANFIS) modelling for nickel adsorption onto agro-wastes and commercial activated carbon. J. Environ. Chem. Eng. 6, 7152–7160 (2018). https://doi.org/10.1016/j.jece.2018.11.013
Teixeira, R.A., Lima, E.C., Benetti, A.D., Thue, P.S., Cunha, M.R., Cimirro, N.F.G.M., Sher, F., Dehghani, M.H., dos Reis, G.S., Dotto, G.L.: Preparation of hybrids of wood sawdust with 3-aminopropyl-triethoxysilane: application as an adsorbent to remove Reactive Blue 4 dye from wastewater effluents. J. Taiwan Inst. Chem. Eng. 125, 141–152 (2021). https://doi.org/10.1016/j.jtice.2021.06.007
Tu, J.V.: Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J. Clin. Epidemiol. 49, 1225–1231 (1996). https://doi.org/10.1016/S0895-4356(96)00002-9
Ullah, Z., Khan, M., Raza Naqvi, S., Farooq, W., Yang, H., Wang, S., Vo, D.-V.N.: A comparative study of machine learning methods for bio-oil yield prediction—a genetic algorithm-based features selection. Biores. Technol. 335, 125292 (2021). https://doi.org/10.1016/j.biortech.2021.125292
Vieira, Y., Schnorr, C., Piazzi, A.C., Netto, M.S., Piccini, W.M., Franco, D.S.P., Mallmann, E.S., Georgin, J., Silva, L.F.O., Dotto, G.L.: An advanced combination of density functional theory simulations and statistical physics modeling in the unveiling and prediction of adsorption mechanisms of 2,4-D pesticide to activated carbon. J. Mol. Liq. 361, 119639 (2022). https://doi.org/10.1016/j.molliq.2022.119639
Wamba, A.G.N., Lima, E.C., Ndi, S.K., Thue, P.S., Kayem, J.G., Rodembusch, F.S., dos Reis, G.S., de Alencar, W.S.: Synthesis of grafted natural pozzolan with 3-aminopropyltriethoxysilane: preparation, characterization, and application for removal of Brilliant Green 1 and Reactive Black 5 from aqueous solutions. Environ. Sci. Pollut. Res. 24, 21807–21820 (2017). https://doi.org/10.1007/s11356-017-9825-4
Wang, P., Wang, X., Yu, S., Zou, Y., Wang, J., Chen, Z., Alharbi, N.S., Alsaedi, A., Hayat, T., Chen, Y., Wang, X.: Silica coated Fe 3 O 4 magnetic nanospheres for high removal of organic pollutants from wastewater. Chem. Eng. J. 306, 280–288 (2016). https://doi.org/10.1016/j.cej.2016.07.068
Westreich, D., Lessler, J., Funk, M.J.: Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression. J. Clin. Epidemiol. 63, 826–833 (2010). https://doi.org/10.1016/j.jclinepi.2009.11.020
Yadav, S., Yadav, A., Bagotia, N., Sharma, N., Sharma, A.K., Kumar, S.: Simultaneous adsorption of three anionic dyes at neutral pH from their individual and multi-component systems on a CTAB modified Pennisetum glaucum based carbon nanotube green composite: adsorption mechanism and process optimization by Box-Behnken design model. J. Mol. Liq. 358, 119223 (2022). https://doi.org/10.1016/j.molliq.2022.119223
Yazidi, A., Sellaoui, L., Dotto, G.L., Bonilla-Petriciolet, A., Fröhlich, A.C., Lamine, A.B.: Monolayer and multilayer adsorption of pharmaceuticals on activated carbon: application of advanced statistical physics models. J. Mol. Liq. 283, 276–286 (2019). https://doi.org/10.1016/j.molliq.2019.03.101
Zhou, J., Li, E., Wei, H., Li, C., Qiao, Q., Armaghani, D.J.: Random forests and cubist algorithms for predicting shear strengths of rockfill materials. Appl. Sci. 9, 1621 (2019). https://doi.org/10.3390/app9081621
Zhu, M.-X., Lee, L., Wang, H.-H., Wang, Z.: Removal of an anionic dye by adsorption/precipitation processes using alkaline white mud. J. Hazard. Mater. 149, 735–741 (2007). https://doi.org/10.1016/j.jhazmat.2007.04.037
Funding
The authors acknowledge the financial assistance from CAPES, CNPq, and FAPERGS. The authors also acknowledge the financial support from ANP-PRH 52.1.
Author information
Authors and Affiliations
Contributions
HG: conceptualization, methodology, software, validation, formal analysis, writing—original draft. NPGS: conceptualization, resources, writing—review and editing, supervision, funding acquisition. FMM: investigation, writing—review and editing. ÉCL: resources, supervision, writing—review and editing. GLD: resources, supervision, writing—review and editing.
Corresponding author
Ethics declarations
Competing interests
The authors report no competing interests.
Ethical approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gasparetto, H., Lima, É.C., Machado, F.M. et al. Elucidating the black-box nature of data-driven models in the adsorption of reactive red M-2BE on activated carbon and multi-walled carbon nanotubes through SHapley Additive exPlanations. Adsorption (2023). https://doi.org/10.1007/s10450-023-00420-z
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10450-023-00420-z