Logo image
Back
Imputation of missing gas permeability data for polymer membranes using machine learning
Journal article   Open access   Peer reviewed

Imputation of missing gas permeability data for polymer membranes using machine learning

Qi Yuan, Mariagiulia Longo, Aaron W. Thornton, Neil B. McKeown, Bibiana Comesaña-Gándara, Johannes C. Jansen and Kim E. Jelfs
Journal of membrane science [e-journal], Vol.627, 119207
01/06/2021
DOI: https://doi.org/10.1016/j.memsci.2021.119207
pdf
Imputation of missing gas permeability data for polymer membranes using machine learning 4.07 MBDownloadView
Published (Version of record)CC BY V4.0,  Open Access
url
Imputation of missing gas permeability data for polymer membranes using machine learningView
Published (Version of record)CC BY V4.0,  Open

Related links

Metrics

3 File views/ downloads
32 Record Views
68 Times Cited - Web of Science

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

#13 Climate Action

Source: InCites

Abstract

Polymers of intrinsic microporosity (PIMs) Polyimides Database imputation Gas separation membranes Machine learning
Polymer-based membranes have the potential for use in energy efficient gas separations. The successful exploitation of new materials requires accurate knowledge of the transport properties of all gases of interest. Open-source databases of gas permeabilities are of significant potential benefit to the research community. The Membrane Society of Australasia (https://membrane-australasia.org/) hosts a database for experimentally measured and reported polymer gas permeabilities. However, the database is incomplete, limiting its potential use as a research tool. Here, missing values in the database were imputed (filled) using machine learning (ML). The ML model was validated against gas permeability measurements that were not recorded in the database. Through imputing the missing data, it is possible to re-analyse historical polymers and look for potential “missed” candidates with promising gas selectivity. In addition, for systems with limited experimental data, ML using sparse features was performed, and we suggest that once the permeability of CO2 and/or O2 for a polymer has been measured, most other gas permeabilities and selectivities, including those for CO2/CH4 and CO2/N2, can be quantitatively estimated. This early insight into the gas permeability of a new system can be used at an initial stage of experimental measurements to rapidly identify polymer membranes worth further investigation.

Details

Logo image