000163042 001__ 163042
000163042 005__ 20251009133841.0
000163042 0247_ $$2doi$$a10.1016/j.memsci.2025.124708
000163042 0248_ $$2sideral$$a145535
000163042 037__ $$aART-2025-145535
000163042 041__ $$aeng
000163042 100__ $$aCarrillo-Sánchez, Lucía$$uUniversidad de Zaragoza
000163042 245__ $$aMembrane preparation assisted by integration of machine learning and response surface methodology for CO2 separation
000163042 260__ $$c2025
000163042 5060_ $$aAccess copy available to the general public$$fUnrestricted
000163042 5203_ $$aThe separation of carbon dioxide (CO2) is presented as a current challenge in the environment and energy sector. The primary reason for this is to control the emissions of this gas into the atmosphere and the upgrading of biomethane. In this context, the membrane separation technology seems to be a very sustainable promising tool for such tasks. This work presents a machine learning (ML) study, based on a database created from membrane preparation conditions and gas separation records from the literature, achieved for the CO2/N2 and CO2/CH4 mixtures using dense membranes of thermoplastic elastomer Pebax® 1657. A comparative analysis of three different ML models was carried out: multiple linear regression, decision tree and random forest. This last algorithm demonstrates the best performance in statistics terms of coefficient of determination and root mean square error. In addition, the combination of the ML random forest with a method based on the design of experiments with response surface methodology (RSM) allowed to identify the favorable conditions for the membrane synthesis, with the objective of enhancing the CO2 separation performance. This resulted in prepared membranes in the laboratory considering the proposed conditions by RSM with CO2 permeability and CO2/X selectivity values of 115 Barrer and 43.5 and 132 Barrer and 16.4 for the CO2/N2 and CO2/CH4 mixtures, respectively, at 35 °C.
000163042 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T68-23R$$9info:eu-repo/grantAgreement/ES/MICIU/CEX2023-001286-S$$9info:eu-repo/grantAgreement/ES/MICIU/PID2022-138582OB-I00$$9info:eu-repo/grantAgreement/ES/MICIU/PRTR-C16.R1
000163042 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc$$uhttps://creativecommons.org/licenses/by-nc/4.0/deed.es
000163042 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000163042 700__ $$0(orcid)0000-0002-4954-1188$$aTéllez, Carlos$$uUniversidad de Zaragoza
000163042 700__ $$0(orcid)0000-0003-1512-4500$$aCoronas, Joaquín$$uUniversidad de Zaragoza
000163042 7102_ $$12009$$2750$$aUniversidad de Zaragoza$$bDpto. Química Analítica$$cÁrea Química Analítica
000163042 7102_ $$15005$$2555$$aUniversidad de Zaragoza$$bDpto. Ing.Quím.Tecnol.Med.Amb.$$cÁrea Ingeniería Química
000163042 773__ $$g736 (2025), 124708 [12 pp.]$$pJ. membr. sci.$$tJOURNAL OF MEMBRANE SCIENCE$$x0376-7388
000163042 8564_ $$s4023647$$uhttps://zaguan.unizar.es/record/163042/files/texto_completo.pdf$$yVersión publicada
000163042 8564_ $$s2706658$$uhttps://zaguan.unizar.es/record/163042/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000163042 909CO $$ooai:zaguan.unizar.es:163042$$particulos$$pdriver
000163042 951__ $$a2025-10-09-13:25:56
000163042 980__ $$aARTICLE