A systematic review of recent advances in the application of machine learning in membrane-based gas separation technologies

Farideh Abdollahi, Arash Khosravi, Seçkin Karagöz and Ahmad Keshavarz

Applied Energy, 2025, vol. 381, issue C, No S030626192402587X

Abstract: Machine learning (ML) has proven to be an effective tool for accelerating the discovery of high-performance polymeric membranes and materials for gas separation. Despite several current articles on this subject, no systematic literature review has been conducted to date. This study aims to bridge this gap by comprehensively reviewing ML concepts, approach, and algorithms in the membrane separation sector. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were used to develop the review. Four online databases, including Web of Science, Scopus, Google Scholar, and Science Direct, were used to screen articles. Study selection, quality assessment, and data extraction were performed independently by four authors. A total of 13,554 studies were retrieved, of which 68 studies (including primary and secondary ones) were included in the final assessment. The fingerprinting and descriptors are two commonly approach for polymer featurization. In terms of algorithms, neural networks (NNs), random forest (RF), and gaussian process regression (GPR) are among the most extensively applied methods. The outcomes of a comprehensive systematic literature review further underscore the diverse and extensive applications of ML in the domain of membrane-based gas separation. These applications encompass the prediction of gas separation performance in various types of membranes, including pure membranes, thin film nanocomposite membranes (TFN), and mixed matrix membranes (MMMs). This review provides the membranologists with an insight into the concept, techniques, case studies, current challenges and limitations of ML in gas separation.

Keywords: Machine learning; Random Forest; PRISMA; Membrane; Gas separation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S030626192402587X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:381:y:2025:i:c:s030626192402587x

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2024.125203

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().