Investigation of light gas adsorption by microporous materials using data analysis and decision tree machine learning algorithm

Authors

  • Thaylane da Rocha Bezerra
  • Sarah Arvelos Altino

DOI:

https://doi.org/10.55905/oelv22n3-066

Keywords:

adsorption, light gases, machine learning, decision tree

Abstract

This study aimed to extract insights into the adsorption behavior of light gases by microporous materials such as zeolites, MOFs, and activated carbons. Data reported in 22 articles published between 1974 and 2022 were analyzed using a decision tree (DT) machine learning algorithm. A comprehensive database comprising 3297 data points, elucidating the impacts of 8 input variables on adsorption capacity, was constructed. Various exploratory data analysis techniques, including histograms, bar charts, and scatter plots, were employed to discern the relationships among input variables and the performance variable. Additionally, a DT model was employed to regress the adsorbed capacity data. Furthermore, a parametric study of this model facilitated the determination of the relative importance of input variables and their partial dependence, enhancing the interpretability of the model and enabling the deduction of heuristics for high or low adsorption capacity. The exploratory data analysis revealed that pressure and molecular mass of the adsorbate were the most significant variables influencing adsorption capacity.

References

ALIBAKSHI, A. Strategies to develop robust neural network models: Prediction of flash point as a case study. Analytica Chimica Acta, v. 1026, p. 69–76, out. 2018.

AL-MUHTASEB, S. A. Adsorption and Desorption Equilibria of Nitrogen, Methane, Ethane, and Ethylene on Date-Pit Activated Carbon. Journal of Chemical & Engineering Data, v. 55, n. 1, p. 313–319, 14 jan. 2010.

AL-MUHTASEB, S. A.; AL-RUB, F. A. A.; ZAROONI, M. AL. Adsorption Equilibria of Nitrogen, Methane, and Ethane on BDH-Activated Carbon. J. Chem. Eng. Data, v. 52, n. 1, p. 60–65, 2007.

AMAR, M. N. et al. Modeling of methane adsorption capacity in shale gas formations using white-box supervised machine learning techniques. Journal of Petroleum Science and Engineering, v. 208, 1 jan. 2022.

BIRKMANN, F. et al. Trace Adsorption of Ethane, Propane, and n -Butane on Microporous Activated Carbon and Zeolite 13X at Low Temperatures. Journal of Chemical & Engineering Data, v. 62, n. 7, p. 1973–1982, 13 jul. 2017.

BOER, D. G. et al. Binderless zeolite LTA beads with hierarchical porosity for selective CO2 adsorption in biogas upgrading. Microporous and Mesoporous Materials, v. 344, p. 112208, out. 2022.

BREIMAN, L. Random Forests. Machine Learning, v. 45, n. 1, p. 5–32, 2001.

CHARALAMBOUS, C. et al. Pure and Binary Adsorption of Carbon Dioxide and Nitrogen on AQSOA FAM Z02. Journal of Chemical & Engineering Data, v. 63, n. 3, p. 661–670, 8 mar. 2018.

CHEN, S.; JIN, L.; CHEN, X. The effect and prediction of temperature on adsorption capability of coal/CH4. Procedia Engineering, v. 26, p. 126–131, 2011.

CHOI, B.-U. et al. Adsorption Equilibria of Methane, Ethane, Ethylene, Nitrogen, and Hydrogen onto Activated Carbon. Journal of Chemical & Engineering Data, v. 48, n. 3, p. 603–607, 18 mar. 2003.

COSTA, E. et al. Equilibrium adsorption of methane, ethane, ethylene, and propylene and their mixtures on activated carbon. Journal of Chemical & Engineering Data, v. 34, n. 2, p. 156–160, 1 abr. 1989.

DANACI, D.; WEBLEY, P. A.; PETIT, C. Guidelines for Techno-Economic Analysis of Adsorption Processes. Frontiers in Chemical Engineering, v. 2, 20 jan. 2021.

DANNER, R.; CHOI, E. C. CORRECTION- Mixture Adsorption Equilibria of Ethane and Ethylene on 13X Molecular Sieves. Industrial & Engineering Chemistry Fundamentals, v. 18, n. 3, p. 300–300, 27 ago. 1979.

DEVORE, J. L. Probability and Statistics for Engineering and the Sciences. 8. ed. Boston: Cengage Learning, 2015.

FREEMAN, J. J.; MCLEOD, A. I. Nitrogen BET surface area measurement as a fingerprint method for the estimation of pore volume in active carbons. Fuel, v. 62, n. 9, p. 1090–1091, set. 1983.

GHANEKAR, P. G.; DESHPANDE, S.; GREELEY, J. Adsorbate chemical environment-based machine learning framework for heterogeneous catalysis. Nature Communications, v. 13, n. 1, p. 5788, 2 out. 2022.

GOLIPOUR, H. et al. Experimental Measurement for Adsorption of Ethylene and Ethane Gases on Copper-Exchanged Zeolites 13X and 5A. Journal of Chemical & Engineering Data, v. 65, n. 8, p. 3920–3932, 13 ago. 2020.

HORSFALL JNR, M.; SPIFF, A. I. Effects of temperature on the sorption of Pb2+ and Cd2+ from aqueous solution by Caladium bicolor (Wild Cocoyam) biomass. Electronic Journal of Biotechnology, v. 8, n. 2, p. 162–169, 15 ago. 2005.

KANG, G. et al. Effect of Pressure and Temperature on CO2/CH4 Competitive Adsorption on Kaolinite by Monte Carlo Simulations. Materials, v. 13, n. 12, p. 2851, 25 jun. 2020.

KARIMI, S.; TAVAKKOLI YARAKI, M.; KARRI, R. R. A comprehensive review of the adsorption mechanisms and factors influencing the adsorption process from the perspective of bioethanol dehydration. Renewable and Sustainable Energy ReviewsElsevier Ltd, , 1 jun. 2019.

KHORAMZADEH, E.; MOFARAHI, M.; LEE, C.-H. Equilibrium Adsorption Study of CO2 and N2 on Synthesized Zeolites 13X, 4A, 5A, and Beta. Journal of Chemical & Engineering Data, v. 64, n. 12, p. 5648–5664, 12 dez. 2019.

KLOUTSE, F. A. et al. Experimental benchmark data of CH4, CO2 and N2 binary and ternary mixtures adsorption on MOF-5. Separation and Purification Technology, v. 197, p. 228–236, maio 2018.

KOOH, M. R. R. et al. Machine learning approaches to predict adsorption capacity of Azolla pinnata in the removal of methylene blue. Journal of the Taiwan Institute of Chemical Engineers, v. 132, p. 104134, mar. 2022.

LANE, D. M. Log Transformations. Disponível em: <https://onlinestatbook.com/2/transformations/log.html>. Acesso em: 12 set. 2023.

LOUKHOVITSKI, B. I.; SHARIPOV, A. S. Molecular Collision Diameters and Electronic Polarizabilities: Inherent Relationship and Fast Evaluation. The Journal of Physical Chemistry A, v. 125, n. 23, p. 5117–5123, 17 jun. 2021.

MARTINS, V. F. D. et al. Ethane/ethylene separation on a copper benzene-1,3,5-tricarboxylate MOF. Separation and Purification Technology, v. 149, p. 445–456, jul. 2015.

MASOUD JAHANDAR, L. et al. Effect of the adsorbate kinetic diameter on the accuracy of the Dubinin–Radushkevich equation for modeling adsorption of organic vapors on activated carbon. Journal of Hazardous Materials, v. 241–242, p. 154–163, nov. 2012.

MCEWEN, J.; HAYMAN, J.-D.; OZGUR YAZAYDIN, A. A comparative study of CO2, CH4 and N2 adsorption in ZIF-8, Zeolite-13X and BPL activated carbon. Chemical Physics, v. 412, p. 72–76, fev. 2013.

MEEK, S. T. et al. Effects of Polarizability on the Adsorption of Noble Gases at Low Pressures in Monohalogenated Isoreticular Metal–Organic Frameworks. The Journal of Physical Chemistry C, v. 116, n. 37, p. 19765–19772, 20 set. 2012.

MENG, M.; ZHONG, R.; WEI, Z. Prediction of methane adsorption in shale: Classical models and machine learning based models. Fuel, v. 278, p. 118358, out. 2020.

MISHRA, P. et al. Adsorption of CO2, CO, CH4 and N2 on a zinc based metal organic framework. Separation and Purification Technology, v. 94, p. 124–130, jun. 2012a.

MISHRA, P. et al. Adsorption of Lower Alkanes on a Zinc Based Metal Organic Framework. Journal of Chemical & Engineering Data, v. 57, n. 9, p. 2610–2613, 13 set. 2012b.

MOREIRA, M. A. et al. Adsorption Equilibrium of Carbon Dioxide, Methane, Nitrogen, Carbon Monoxide, and Hydrogen on UiO-66(Zr)_(COOH) 2. Journal of Chemical & Engineering Data, v. 64, n. 11, p. 4724–4732, 14 nov. 2019.

MUKHIYA, S. K.; AHMED, U. Hands-On Exploratory Data Analysis with Python. 1th. ed. Mumbai: Packt Publishing, 2020.

NAIT AMAR, M. et al. Modeling of methane adsorption capacity in shale gas formations using white-box supervised machine learning techniques. Journal of Petroleum Science and Engineering, v. 208, p. 109226, jan. 2022.

NAKAHARA, T. Calculation of adsorption equilibria for the binary gaseous mixtures on heterogeneous surface. Chemical Engineering Science, v. 41, n. 1, p. 2093–2098, 1986.

PHAM, T. D. et al. Experimental and computational studies on the adsorption of CO2 and N2 on pure silica zeolites. Microporous and Mesoporous Materials, v. 185, p. 157–166, fev. 2014.

PRASAD, K. et al. Predicting the Adsorption Efficiency Using Machine Learning Framework on a Carbon-Activated Nanomaterial. Adsorption Science & Technology, v. 2023, p. 1–11, 2 jun. 2023.

PRAVIN, P. S. et al. Hyperparameter optimization strategies for machine learning-based stochastic energy efficient scheduling in cyber-physical production systems. Digital Chemical Engineering, p. 100047, jul. 2022.

RASCHKA, S.; MIRJALILI, V. Python Machine Learning. 3th. ed. [s.l.] Packt, 2019.

REICH, R. Adsorption on activated carbon of methane, ethane, and ethylene gases and their mixtures and carbon dioxide at 212 K, 260 K, and 301 K and up to thirty-five atmospheres. Thesis—Atlanta, GA: Georgia Institute of Technology , 25 nov. 1974.

SCHÄF, O. et al. Importance of PCDD/F molecules’ polarizability and steric hindrance on their adsorption onto zeolites in a standard EN1948-1 sampling device for incinerator emission monitoring. Chemosphere, v. 259, p. 127457, nov. 2020.

SEIFI, S. et al. Microstructure of Dry Mortars without Cement: Specific Surface Area, Pore Size and Volume Distribution Analysis. Applied Sciences, v. 13, n. 9, p. 5616, 2 maio 2023.

SITU, Y. et al. Large-Scale Screening and Machine Learning for Metal–Organic Framework Membranes to Capture CO2 from Flue Gas. Membranes, v. 12, n. 7, p. 700, 11 jul. 2022.

SPEIGHT, J. G. Hydrogen Production. Em: Heavy Oil Recovery and Upgrading. [s.l.] Elsevier, 2019. p. 657–697.

URSUEGUÍA, D.; DÍAZ, E.; ORDÓÑEZ, S. Adsorption of methane and nitrogen on Basolite MOFs: Equilibrium and kinetic studies. Microporous and Mesoporous Materials, v. 298, p. 110048, maio 2020.

WANG, S. et al. Insights into CO2 /N2 Selectivity in Porous Carbons from Deep Learning. ACS Materials Letters, v. 1, n. 5, p. 558–563, 4 nov. 2019.

WANG, Z. et al. Identification of optimal metal-organic frameworks by machine learning: Structure decomposition, feature integration, and predictive modeling. Computers & Chemical Engineering, v. 160, p. 107739, abr. 2022.

XIE, C. et al. Explainable machine learning for carbon dioxide adsorption on porous carbon. Journal of Environmental Chemical Engineering, v. 11, n. 1, p. 109053, fev. 2023.

ZHANG, W. et al. Modeling, optimization and understanding of adsorption process for pollutant removal via machine learning: Recent progress and future perspectives. Chemosphere, v. 311, p. 137044, jan. 2023.

ZHANG, Y. et al. Adsorption Equilibrium of N2 , CH4 , and CO2 on MIL-101. Journal of Chemical & Engineering Data, v. 60, n. 10, p. 2951–2957, 8 out. 2015.

Published

2024-03-08

How to Cite

Bezerra, T. da R., & Altino, S. A. (2024). Investigation of light gas adsorption by microporous materials using data analysis and decision tree machine learning algorithm. OBSERVATÓRIO DE LA ECONOMÍA LATINOAMERICANA, 22(3), e3668. https://doi.org/10.55905/oelv22n3-066

Issue

Section

Articles