Machine Learning for Finding Materials for Membranes

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 3 | 01 | Page :
    By

    V. Basil Hans,

  1. Research Professor, Department of Commerce and Management, Srinivas University in Mangalore, Mangalore, India

Abstract

Traditionally, finding and improving membrane materials has depended on trial-and-error experiments, which can take a long time, cost a lot of money, and only cover a small area. Recent improvements in machine learning (ML) have the potential to change the way membrane materials are designed by making it possible to make predictions about performance, selectivity, and stability based on data. ML algorithms can find hidden links between the structure, composition, and separation efficiency of membranes. This can help scientists design new materials for gas separation, water purification, and energy use in a logical way. Machine learning (ML) frameworks can quickly search across large chemical spaces to find the best polymer chemistries, nanoporous architectures, and mixed-matrix membrane topologies by combining computational modelling, high-throughput simulations, and experimental data. Additionally, the integration of machine learning with molecular dynamics and density functional theory improves comprehension of nanoscale transport mechanisms. Even if a lot of progress has been made, there are still problems with standardising data, making models understandable, and adding experimental feedback loops. To create strong, generalisable models that can lead to the next generation of high-performance, sustainable membrane technologies, these problems need to be solved.

Keywords: Machine learning, membrane materials, data-driven design, and molecular modelling Material informatics, predictive modelling, and separation performance

How to cite this article:
V. Basil Hans. Machine Learning for Finding Materials for Membranes. International Journal of Membranes. 2026; 03(01):-.
How to cite this URL:
V. Basil Hans. Machine Learning for Finding Materials for Membranes. International Journal of Membranes. 2026; 03(01):-. Available from: https://journals.stmjournals.com/ijm/article=2026/view=238399


References

  1. Krishnapriyan AS, Montoya J, Haranczyk M, Hummelshøj J, Morozov D. Machine learning utilizing persistent homology and chemical word embeddings enhances prediction accuracy and interpretability in metal–organic frameworks. Sci Rep. 2021 Apr 26;11(1):8888. doi:10.1038/s41598-021-88027-8.
  2. Glass S, Schmidt M, Merten P, Abdul Latif A, et Design of modified polymer membranes using machine learning. 2024. Available from: https://www.ncbi.nlm.nih.gov.
  3. Maleki R, Shams SM, Mehdizadeh Chellehbari Y, Rezvantalab S, et Materials discovery of ion- selective membranes using artificial intelligence. 2022. Available from: https://www.ncbi.nlm.nih.gov.
  4. Yu The use of machine learning in the life of materials. arXiv preprint arXiv:1707.04826. 2017. Available from: https://arxiv.org.
  5. Oliveira ON, Oliveira Materials discovery with machine learning and knowledge discovery. 2022. Available from: https://www.ncbi.nlm.nih.gov.
  6. Giro R, Hsu H, Kishimoto A, et al. AI-powered automated discovery of polymer membranes for carbon capture. npj Comput Mater. 2023;9:133. doi:10.1038/s41524-023-01088-3.
  7. Conrad F, Mälzer M, Schwarzenberger M, Wiemer H, et Benchmarking AutoML for regression tasks on small tabular data in materials design. 2022. Available from: https://www.ncbi.nlm.nih.gov.
  8. Nunes SP, Culfaz-Emecen ZP, Ramon GZ, Visser T, Koops GH, Jin W, et al. Thinking the future of membranes: perspectives for advanced and new membrane materials and manufacturing processes. J Membr Sci. 2020 Mar 15;598:117761. doi:10.1016/j.memsci.2019.117761.
  9. Talukder MJ, Alshami AS, Tayyebi A, Ismail N, Yu Membrane science meets machine learning: future potential in assisting membrane material design and fabrication. Sep Sci Technol. 2023 May 11. doi:10.1080/15422119.2023.2212295.
  10. Lee KP, Arnot TC, Mattia D. A review of reverse osmosis membrane materials for desalination: development to date and future possibilities. J Membr Sci. 2011 Mar 15;370(1–2):1-22. doi:10.1016/j.memsci.2010.12.036.
Ahead of Print Subscription Review Article
Volume 03
01
Received 10/11/2025
Accepted 13/12/2025
Published 20/01/2026
Publication Time 71 Days
71

Login


My IP

PlumX Metrics