Nashrieh Shimi va Mohandesi Shimi Iran

Nashrieh Shimi va Mohandesi Shimi Iran

Application of Machine Learning to provide an insight into Chemical and Structural Features of Polymeric Membranes for CO2 Capture

Document Type : Research Article

Authors
Farideh Abdollahi 1
Arash Khosravi 1
Ahmad Keshavarz 2
Seckin Karagoz 3
1 Sustainable Membrane Technology Research Group (SMTRG), Chemical Engineering Department, Persian Gulf University (PGU), Bushehr, I.R. IRAN
2 IoT and Signal Processing Research Group, ICT Research Institute, Faculty of Intelligent Systems Engineering and Data Science, Persian Gulf University, Bushehr, I.R. IRAN
3 Department of Chemical Engineering, College of Engineering, Qatar University, Doha, Qatar
Abstract
In recent years, the application of membrane technologies has increased for both gas separation and carbon capture and Artificial Intelligence (AI) can play a crucial role in reducing the costs and removing the implementation related hurdles of these technologies. In this study, in order to address the limitation of experimental research and accelerate the pace of identifying new and effective membranes for being used in the gas industry, a Machine Learning (ML) technique has been developed based on polymers' physical and chemical properties. In particular, the Random Forest (RF) algorithm is used to predict membrane performance in terms of permeability and selectivity for CO2/CH4 separation. Then, the Shapley Additive Explanations (SHAP) method was used to interpret the results. In addition, in order to introduce polymers to ML model, fingerprinting and molecular descriptor approaches were used simultaneously.  The results proved that the Topological Polar Surface Area (TPSA) is one of the most influential parameters on membrane performance. Furthermore, findings revealed that polar groups in polymer backbone structure have a negative effect on permeability, while they are positively correlated with selectivity. Another outcome of the present study was about the negative effect of aromatic rings on membranes permeability.
Keywords
Machine learning
Random forest
Polymeric membrane
Gas separation
SHAP

Subjects

[1] Zhang Y., Sunarso J., Liu S., Wang R., Current status and Development of Membranes for CO2/CH4 Separation: A Review, International Journal of Greenhouse Gas Control, 12: 84-107 (2013).
[2] Baker R.W., Membrane Technology and Applications, John Wiley & Sons, (2012).
[3] Abdollahi F., Hashemifard S., Khosravi A., Matsuura T., Heat and Mass Transfer Modeling of an Energy Efficient Hybrid Membrane-Based Air Conditioning System for Humid Climates, Journal of Membrane Science, 625: 119179 (2021).
[4] Robeson L.M., The Upper Bound Revisited, Journal of membrane science, 320(1-2): 390-400 (2008).
[5] Nobakht D., Abedini R., Improved gas Separation Performance of Pebax®1657 Membrane Modified by Poly-Alcoholic Compounds, Journal of Environmental Chemical Engineering, 10(3): 107568  (2022).
[6] Kong J., Liu J., Jia P., Qi N., Chen Z., Xu S., Li N., Synergistic Effect of Thermal Crosslinking and Thermal Rearrangement on Free Volume and Gas Separation Properties of 6FDA Based Polyimide Membranes Studied by Positron Annihilation, Journal of Membrane Science, 645: 120163 (2022).
[7] Guan J., Huang T., Liu W., Feng F., Japip S., Li J., Wang X., Zhang S., Design and Prediction of Metal Organic Framework-Based Mixed Matrix Membranes for CO2 Capture Via Machine Learning, Cell Reports Physical Science, 3(5): 100864 (2022).
[8] Barnett J.W., Bilchak C.R., Wang Y., Benicewicz B.C., Murdock L.A., Bereau T., Kumar S.K., Designing Exceptional Gas-Separation Polymer Membranes Using Machine Learning, Science advances, 6(20): eaaz4301 (2020).
[9] Tao L., Chen G., Li Y., Machine Learning Discovery of High-Temperature Polymers, Patterns, 2(4): 100225 (2021).
[10] Zhu G., Kim C., Chandrasekarn A., Everett J.D., Ramprasad R., Lively R.P., Polymer Genome–Based Prediction of Gas Permeabilities in Polymers, Journal of Polymer Engineering, 40(6): 451-457 (2020).
[11] Alihosseini A., Hedayati Moghaddam A., Permeability and Selectivity Prediction of Poly (4-Methyl 1-Pentane) Membrane Modified by Nanoparticles in Gas Separation Through Artificial Intelligent Systems, Polyolefins Journal, 7(2): 91-98 (2020).
[12] Lipu M.H., Ayob A., Saad M., Hussain A., Hannan M., Faisal M., State of Charge Estimation for Lithium-ion Battery Based on Random Forests Technique with Gravitational Search Algorithm, 2018 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), IEEE, 45-50 (2018).
[13] Efron B., Tibshirani R., Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy, Statistical science, 54-75 (1986).
[14] Boehmke B., Greenwell B., Hands-on Machine Learning with R, Chapman and Hall/CRC, (2019).
[15] Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Scikit-Learn: Machine Learning in Python, the Journal of machine Learning research, 12:  2825-2830 (2011).
[16] Meng Y., Yang N., Qian Z., Zhang G., What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values, Journal of Theoretical and Applied Electronic Commerce Research, 16(3): 466-490 (2020).
[17] Rodríguez-Pérez R., Bajorath J., Interpretation of Machine Learning Models Using Shapley Values: Application to Compound Potency and Multi-Target Activity Predictions, Journal of computer-aided molecular design, 34(10): 1013-1026 (2020).
[18] Thornton A., BD F., Robeson L., Polymer Gas Separation Membrane Database, (2012), Online.
[19] Weininger D., SMILES, a Chemical Language and Information System. 1. Introduction to Methodology and Encoding Rules, Journal of chemical information and computer sciences, 28(1): 31-36 (1988).
[20] Landrum G., RDKit: A Software Suite for Cheminformatics, Computational Chemistry, and Predictive Modeling, Greg Landrum, (2013).
[21] Nedelman J., Wallenius T., Bernoulli Trials, Poisson Trials, Surprising Variances, and Jensen's Inequality, The American Statistician, 40(4): 286-289 (1986).
[22] Lubo-Robles D., Devegowda D., Jayaram V., Bedle H., Marfurt K.J., Pranter M.J., Machine Learning Model Interpretability Using SHAP Values: Application to a Seismic Facies Classification Task, SEG International Exposition and Annual Meeting, OnePetro, (2020).
[23] Fernandes J., Gattass C.R., Topological Polar Surface Area Defines Substrate Transport by Multidrug Resistance Associated Protein 1 (MRP1/ABCC1), Journal of medicinal chemistry, 52(4): 1214-1218 (2009).
[24] McKeen L.W., Permeability Properties of Plastics and Elastomers, William Andrew, (2016).
[25] Recio R., Lozano A.E., Prádanos P., Marcos A., Tejerina F., Hernández A., Effect of Fractional Free Volume and Tg on Gas Separation Through Membranes Made with Different Glassy Polymers, Journal of applied polymer science, 107(2): 1039-1046 (2008).
[26] Hamouda S.B., Nguyen Q.T., Langevin D., Roudesli S., Poly(Vinylalcohol)/Poly(Ethyleneglycol) /Poly(Ethyleneimine) Blend Membranes - Structure and CO2 Facilitated Transport, Comptes Rendus Chimie, 13(3): 372-379 (2010).
[27] Bicerano J., Prediction of Polymer Properties, cRc Press, (2002).
[28] Chan D., Chien J.C., Axpe E., Blankemeier L., Baker S.W., Swaminathan S., Piunova V.A., Zubarev D.Y., Maikawa C.L., Grosskopf A.K., Combinatorial Polyacrylamide Hydrogels for Preventing Biofouling on Implantable Biosensors, Advanced Materials, 2109764 (2022).
[29] Mulder M., Mulder J., Basic Principles of Membrane Technology, Springer science & business media, (1996).
[30] Kadirkhan F., Goh P.S., Ismail A.F., Wan Mustapa W.N.F., Halim M.H.M., Soh W.K., Yeo S.Y., Recent Advances of Polymeric Membranes in Tackling Plasticization and Aging for Practical Industrial CO2/CH4 Applications—A Review, Membranes, 12(1): 71 (2022).
[31] Guzmán-Lucero D., Froylán Palomeque-Santiago J., Camacho-Zúñiga C., Ruiz-Treviño F.A., Guzmán J., Galicia-Aguilar A., Aguilar-Lugo C., Gas Permeation Properties of Soluble Aromatic Polyimides Based on 4-Fluoro-4,4'-Diaminotriphenylmethane, Materials, 8(4): 1951-1965 (2015).
[32] Liu J., Zhang S., Jiang D.-e., Doherty C.M., Hill A.J., Cheng C., Park H.B., Lin H., Highly Polar But Amorphous Polymers with Robust Membrane CO2/N2 Separation Performance, Joule, 3(8): 1881-1894 (2019).
[33] Yang J., Tao L., He J., McCutcheon J., Li Y., Discovery of Innovative Polymers for Next-Generation Gas-Separation Membranes using Interpretable Machine Learning, (2021).
[34] Sanders D.F., Smith Z.P., Guo R., Robeson L.M., McGrath J.E., Paul D.R., Freeman B.D., Energy-Efficient Polymeric Gas Separation Membranes for a Sustainable Future: A Review, Polymer, 54(18): 4729-4761 (2013).
[35] Matteucci S., Yampolskii Y., Freeman B.D., Pinnau I., Transport of Gases and Vapors in Glassy and Rubbery Polymers, Materials science of membranes for gas and vapor separation, 1: 1-2 (2006).
[36] Wu A.X., Drayton J.A., Rodriguez K.M., Qian Q., Lin S., Smith Z.P., Influence of Aliphatic and Aromatic Fluorine Groups on Gas Permeability and Morphology of Fluorinated Polyimide Films, Macromolecules, 53(13): 5085-5095 (2020).
[37] Han Y., Ho W.W., Polymeric Membranes for CO2 Separation and Capture, Journal of Membrane Science, 628: 119244 (2021).
[38] Hashemifard S.A., Khosravi A., Abdollahi F., Alihemati Z., Rezaee M., Chapter 11 - Synthetic polymeric Membranes for Gas and Vapor Separations, Synthetic Polymeric Membranes for Advanced Water Treatment, Gas Separation, and Energy Sustainability, Elsevier, 217-272 (2020).