Recommended by

Indexed by

AI powered, automated discovery of polymer membranes for carbon capture

Ronaldo Giro1*, Hsianghan Hsu2, Akihiro Kishimoto2, Toshiyuki Hama2, Rodrigo F. Neumann1, Binquan Luan3, Seiji Takeda2, Lisa Hamada2, Mathias B. Steiner1

1 IBM Research Brazil - Avenida Rep├║blica do Chile, 330 - 11o. e 12. andares Rio De Janeiro, RJ 20031-170, Brazil

2 IBM Research Tokyo - 7-7 Shinkawasaki Saiwai-Ku Kawasaki, 14 212-0032, Japan

3 IBM Research - 1101 Kitchawan Rd PO Box 218 Yorktown Heights, NY 10598-0218, USA

* Corresponding authors emails: rgiro@br.ibm.com
DOI10.24435/materialscloud:64-c8 [version v7]

Publication date: Jan 30, 2023

How to cite this record

Ronaldo Giro, Hsianghan Hsu, Akihiro Kishimoto, Toshiyuki Hama, Rodrigo F. Neumann, Binquan Luan, Seiji Takeda, Lisa Hamada, Mathias B. Steiner, AI powered, automated discovery of polymer membranes for carbon capture, Materials Cloud Archive 2023.20 (2023), https://doi.org/10.24435/materialscloud:64-c8


Data sets and scripts for computational discovery of polymer membranes for carbon dioxide separation. The training data set with 1,169 homo-polymers provides carbon dioxide permeability, glass transition temperature and half decomposition temperature for each listed material. The output data set contains 784 optimized homo-polymer candidates generated by Inverse Design and Machine Learning techniques. The Jupyter notebook enables the use of the Polymer Property Prediction Engine as a service for generating the properties provided in the training data set.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.


File name Size Description
11.1 KiB Jupyter notebook with an example of how to use the Polymer Property Prediction Engine with APIs (application programming interface)
550 Bytes Input file data-set for the Jupyter notebook
189.1 KiB 1,169 calculated homo-polymers properties: IUPAC polymer name, OPSIN SMILES, log10( CO2 permeability (Barrer)), glass transition temperature (K) and half decomposition temperature (K)
81.7 KiB 784 homopolymers generated by Inverse Design and Machine Learning techniques with the OPSIN SMILES, glass transition temperature (Tg), half decomposition temperature (Thf) and CO2 permeability (PCO2). Tg and Thf are calculated using Polymer Property Prediction Engine, and PCO2 was calculated by the Machine Learning regression model.
291.6 KiB Jupyter notebook for the training and regression models with the open-source version of IMD engine which is available at: https://github.com/GT4SD/molgx-core/


Files and data are licensed under the terms of the following license: Materials Cloud non-exclusive license to distribute v1.0. CDLA-Sharing-1.0
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Preprint (Preprint where the data is discussed)
Journal reference (Paper in which the published data is described)


Polymeric membranes CO2 separation Carbon dioxide separation