Prediksi Adsorpsi Zat Warna Metilene Biru Pada Karbon Aktif Menggunakan Machine Learning
Abstract
Pemanfaatan teknologi informasi dalam membantu mengurangi kegiatan eksperimen di laboratorium semakin meningkat. Pemanfaatan teknologi informasi akan menghemat bahan, waktu dan biaya, serta tentunya akan mengurangi resiko bahaya yang kemungkinan timbul jika dilakukan percobaan secara langsung di laboratorium. Salah satu teknologi informasi yang sedang berkembang dan menarik untuk digunakan adalah machine learning. Penelitian ini bertujuan untuk mengetahui unjuk kerja model machine learning dalam memprediksi adsorpsi metilene biru pada karbon aktif. Dataset adsorpsi metilene biru menggunakan karbon aktif biji alpukat dari penelitian terdahulu yang dilakukan oleh Regti dkk (2017) dibagi menjadi data latihan dan data tes. Dengan data tersebut kemudian digunakan untuk menguji performa model machine learning (neural networks, support vector machines, random forest, dan linear regression) menggunakan metode Stratified 10-fold Cross validation. Model neural network merupakan model machine learning terbaik untuk memprediksi proses adsorpsi metilene biru pada karbon aktif dibandingkan dengan model SVM, Random Forest maupun regresi linier dengan performa prediksi terbaik pada data latihan maupun data uji. Nilai MSE 14.640, RMSE 3.826, MAE 3.178 dan R2 0.975 pada data latihan dan pada data uji nilai MSE 3.51e-06, RMSE 0.00187, MAE 0.00135 dan R2 0.999.
Keywords
Full Text:
PDFReferences
Ahmad, M. B., Soomro, U., Muqeet, M., & Ahmed, Z. (2021). Adsorption of Indigo Carmine dye onto the surface-modified adsorbent prepared from municipal waste and simulation using deep neural network. Journal of Hazardous Materials, 408, 124433. https://doi.org/10.1016/j.jhazmat.2020.124433
Ahmed, M. B., Hasan Johir, M. A., Zhou, J. L., Ngo, H. H., Nghiem, L. D., Richardson, C., Moni, M. A., & Bryant, M. R. (2019). Activated carbon preparation from biomass feedstock: Clean production and carbon dioxide adsorption. Journal of Cleaner Production, 225, 405–413. https://doi.org/10.1016/j.jclepro.2019.03.342
Albalasmeh, A., Gharaibeh, M. A., Mohawesh, O., Alajlouni, M., Quzaih, M., Masad, M., & El Hanandeh, A. (2020). Characterization and Artificial Neural Networks Modelling of methylene blue adsorption of biochar derived from agricultural residues: Effect of biomass type, pyrolysis temperature, particle size. Journal of Saudi Chemical Society, 24(11), 811–823. https://doi.org/10.1016/j.jscs.2020.07.005
Asfaram, A., Ghaedi, M., Azqhandi, M. H. A., Goudarzi, A., & Dastkhoon, M. (2016). Statistical experimental design, least squares-support vector machine (LS-SVM) and artificial neural network (ANN) methods for modeling the facilitated adsorption of methylene blue dye. RSC Advances, 6(46), 40502–40516. https://doi.org/10.1039/C6RA01874B
Berkane, N., Meziane, S., & Aziri, S. (2019). Optimization of Congo red removal from aqueous solution using Taguchi experimental design. Separation Science and Technology, 1–11. https://doi.org/10.1080/01496395.2019.1577442
Chibani, S., & Coudert, F.-X. (2020). Machine learning approaches for the prediction of materials properties. APL Materials, 8(8), 080701. https://doi.org/10.1063/5.0018384
de Miranda Ramos Soares, A. P., de Oliveira Carvalho, F., de Farias Silva, C. E., da Silva Gonçalves, A. H., & de Souza Abud, A. K. (2020). Random Forest as a promising application to predict basic-dye biosorption process using orange waste. Journal of Environmental Chemical Engineering, 8(4), 103952. https://doi.org/10.1016/j.jece.2020.103952
Drajana, I. C. R. (2017). METODE SUPPORT VECTOR MACHINE DAN FORWARD SELECTION PREDIKSI PEMBAYARAN PEMBELIAN BAHAN BAKU KOPRA. ILKOM Jurnal Ilmiah, 9(2), 116–123. https://doi.org/10.33096/ilkom.v9i2.134.116-123
Fanourgakis, G. S., Gkagkas, K., Tylianakis, E., & Froudakis, G. (2020). A Generic Machine Learning Algorithm for the Prediction of Gas Adsorption in Nanoporous Materials. The Journal of Physical Chemistry C, 124(13), 7117–7126. https://doi.org/10.1021/acs.jpcc.9b10766
Ghaedi, A. M., & Vafaei, A. (2017). Applications of artificial neural networks for adsorption removal of dyes from aqueous solution: A review. Advances in Colloid and Interface Science, 245, 20–39. https://doi.org/10.1016/j.cis.2017.04.015
Ghorai, S., Sarkar, A., Raoufi, M., Panda, A. B., Schönherr, H., & Pal, S. (2014). Enhanced Removal of Methylene Blue and Methyl Violet Dyes from Aqueous Solution Using a Nanocomposite of Hydrolyzed Polyacrylamide Grafted Xanthan Gum and Incorporated Nanosilica. ACS Applied Materials & Interfaces, 6(7), 4766–4777. https://doi.org/10.1021/am4055657
González-García, P. (2018). Activated carbon from lignocellulosics precursors: A review of the synthesis methods, characterization techniques and applications. Renewable and Sustainable Energy Reviews, 82, 1393–1414. https://doi.org/10.1016/j.rser.2017.04.117
Hafsa, N., Rushd, S., Al-Yaari, M., & Rahman, M. (2020). A Generalized Method for Modeling the Adsorption of Heavy Metals with Machine Learning Algorithms. Water, 12(12), 3490. https://doi.org/10.3390/w12123490
Hocking, R. R. (2003). Methods and Applications of Linear Models: Regression and the Analysis of Variance. John Wiley & Sons, Inc. https://doi.org/10.1002/0471434159
Jaria, G., Calisto, V., Silva, C. P., Gil, M. V., Otero, M., & Esteves, V. I. (2019). Obtaining granular activated carbon from paper mill sludge – A challenge for application in the removal of pharmaceuticals from wastewater. Science of The Total Environment, 653, 393–400. https://doi.org/10.1016/j.scitotenv.2018.10.346
Jatmiko, T. (2020). Optimization of Production Activated Carbon for Removal of Pharmaceuticals Waste Using Taguchi Method and Grey Relational Analysis. Jurnal Riset Teknologi Pencegahan Pencemaran Industri, 11(2), 11–18. https://doi.org/10.21771/jrtppi.2020.v11.no2.p11-18
Jatmiko, T. H., Prasetyo, D. J., & Pulungan, N. A. (2018). Analisis Kinerja Reaktor Unggun Tetap untuk Produksi Hidrogen Melalui Reaksi Steam Reforming Etanol. Jurnal Riset Teknologi Industri, 12(1), 56–65. https://doi.org/10.26578/jrti.v12i1.3622
Jatmiko, T. H., & Pratiwi, D. (2019). Metode Taguchi Untuk Optimasi Adsorpsi Zat Warna Metilen Biru Dengan Karbon Aktif. Prosiding Seminar Nasional Industri Kerajinan Dan Batik, 1(1), C1–C1.
Jiang, W., Xing, X., Li, S., Zhang, X., & Wang, W. (2019). Synthesis, characterization and machine learning based performance prediction of straw activated carbon. Journal of Cleaner Production, 212, 1210–1223. https://doi.org/10.1016/j.jclepro.2018.12.093
Kiraz, A., Canpolat, O., Erkan, E. F., & Özer, Ç. (2019). Artificial neural networks modeling for the prediction of Pb(II) adsorption. International Journal of Environmental Science and Technology, 16(9), 5079–5086. https://doi.org/10.1007/s13762-018-1798-4
Kooh, M. R. R., Dahri, M. K., & Lim, L. B. L. (2018). Jackfruit seed as low-cost adsorbent for removal of malachite green: Artificial neural network and random forest approaches. Environmental Earth Sciences, 77(12), 434. https://doi.org/10.1007/s12665-018-7618-9
Li, M., Wei, D., Liu, T., Liu, Y., Yan, L., Wei, Q., Du, B., & Xu, W. (2019). EDTA functionalized magnetic biochar for Pb(II) removal: Adsorption performance, mechanism and SVM model prediction. Separation and Purification Technology, 227, 115696. https://doi.org/10.1016/j.seppur.2019.115696
Pathania, D., Sharma, S., & Singh, P. (2017). Removal of methylene blue by adsorption onto activated carbon developed from Ficus carica bast. Arabian Journal of Chemistry, 10, S1445–S1451. https://doi.org/10.1016/j.arabjc.2013.04.021
Patil, M. A., Shinde, J. K., Jadhav, A. L., & Deshpande, S. R. (2017). Adsorption of Methylene Blue in waste water by low cost adsorbent Rice husk. 10(1), 7.
Pauletto, P. S., Dotto, G. L., & Salau, N. P. G. (2020). Optimal artificial neural network design for simultaneous modeling of multicomponent adsorption. Journal of Molecular Liquids, 320, 114418. https://doi.org/10.1016/j.molliq.2020.114418
Prakash, K. B., Ruwali, A., & Kanagachidambaresan, G. R. (2021). Regression. In K. B. Prakash & G. R. Kanagachidambaresan (Eds.), Programming with TensorFlow: Solution for Edge Computing Applications (pp. 23–37). Springer International Publishing. https://doi.org/10.1007/978-3-030-57077-4_4
Regti, A., Laamari, M. R., Stiriba, S.-E., & El Haddad, M. (2017). Use of response factorial design for process optimization of basic dye adsorption onto activated carbon derived from Persea species. Microchemical Journal, 130, 129–136. https://doi.org/10.1016/j.microc.2016.08.012
Vargas, A. M. M., Cazetta, A. L., Kunita, M. H., Silva, T. L., & Almeida, V. C. (2011). Adsorption of methylene blue on activated carbon produced from flamboyant pods (Delonix regia): Study of adsorption isotherms and kinetic models. Chemical Engineering Journal, 168(2), 722–730. https://doi.org/10.1016/j.cej.2011.01.067
Yu, L., & Luo, Y. (2014). The adsorption mechanism of anionic and cationic dyes by Jerusalem artichoke stalk-based mesoporous activated carbon. Journal of Environmental Chemical Engineering, 2(1), 220–229. https://doi.org/10.1016/j.jece.2013.12.016
DOI: http://dx.doi.org/10.22322/dkb.v39i1.6936
Refbacks
- There are currently no refbacks.
Copyright (c) 2022 Tri Hadi Jatmiko
This work is licensed under a Creative Commons Attribution 4.0 International License.
Dinamika Kerajinan dan Batik : Majalah Ilmiah indexeed by :
