journal article·2025Open access

A data-driven approach to interfacial polymerization exploiting machine learning for predicting thin-film composite membrane formation

Gergo Ignacz, Muhammad Irshad Baig, Karuppasamy Gopalsamy, Andres Villa, Suzana Nunes, Bernard Ghanem, Tejus Shastry, Sanat K. Kumar, Gyorgy Szekely

Materials Horizons· Volume 12· Issue 21

Abstract

AFM and optical microscopy. This unprecedentedly large and open access dataset marks a considerable step toward data-driven thin-film membrane development. We trained five machine learning models on molecular structures and density functional theory calculations to study film formation parameters and their binary outcomes. The results indicate that film formation can be predicted directly from monomers, facilitating the potential of data-driven membrane development. Our work shifts the focus from performance prediction to the fundamental step of thin-film formation, offering a new perspective in data-driven membrane research.
Source: openalex_inverted_index · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Software System Performance and Reliability · Machine Learning in Materials Science

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Advanced Membranes and Porous Materials Center, Chemical Engineering Program, Physical Science and Engineering Division (PSE), King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia

Computer, Electrical and Mathematical Science and Engineering Division (CEMSE), King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia

Department of Chemical Engineering, Columbia University, New York 10027, USA

Funding

King Abdullah University of Science and Technology

References (58)

Show source-provided references
1. Zhang · Angew. Chem., Int. Ed. · 2020 · 59 · 2184010.1002/anie.201916473 ↗
2. Song · Mater. Chem. Front. · 2017 · 1 · 102810.1039/c6qm00325g ↗
3. Jimenez-Solomon · Nat. Mater. · 2016 · 15 · 76010.1038/nmat4638 ↗
4. Alf · Adv. Mater. · 2010 · 22 · 199310.1002/adma.200902765 ↗
5. Lee · Nano Lett. · 2006 · 6 · 230510.1021/nl061776m ↗
6. Lin · J. Membr. Sci. · 2016 · 497 · 36510.1016/j.memsci.2015.09.020 ↗
7. Tan · Adv. Sci. · 2023 · 10 · 220688810.1002/advs.202206888 ↗
8. Lee · J. Membr. Sci. · 2023 · 672 · 12143810.1016/j.memsci.2023.121438 ↗
9. Alhazmi · Nat. Commun. · 2024 · 15 · 715110.1038/s41467-024-51548-7 ↗
10. Wen · Nat. Commun. · 2022 · 13 · 614710.1038/s41467-022-33821-9 ↗
11. Jin · Angew. Chem. · 2024 · 63 · e20240589110.1002/ange.202405891 ↗
12. Ignacz · J. Membr. Sci. · 2023 · 674 · 12151910.1016/j.memsci.2023.121519 ↗
13. Hu · J. Membr. Sci. · 2023 · 679 · 12170110.1016/j.memsci.2023.121701 ↗
14. Fetanat · Sep. Purif. Technol. · 2021 · 270 · 11838310.1016/j.seppur.2021.118383 ↗
15. Rall · J. Membr. Sci. · 2019 · 569 · 20910.1016/j.memsci.2018.10.013 ↗
16. Rall · J. Membr. Sci. · 2020 · 600 · 11786010.1016/j.memsci.2020.117860 ↗
17. Wang · Environ. Sci. Technol. · 2023 · 57 · 1591410.1021/acs.est.3c04773 ↗
18. Wang · Sep. Purif. Technol. · 2023 · 304 · 12232810.1016/j.seppur.2022.122328 ↗
19. Sutariya · Sep. Purif. Technol. · 2025 · 354 · 12896010.1016/j.seppur.2024.128960 ↗
20. Coley · ACS Cent. Sci. · 2017 · 3 · 43410.1021/acscentsci.7b00064 ↗
21. Van Buggenhout · J. Membr. Sci. · 2025 · 713 · 12335610.1016/j.memsci.2024.123356 ↗
22. An · J. Membr. Sci. · 2019 · 583 · 3110.1016/j.memsci.2019.04.050 ↗
23. Ghosh · J. Membr. Sci. · 2008 · 311 · 3410.1016/j.memsci.2007.11.038 ↗
24. Kim · Environ. Sci. Technol. · 2005 · 39 · 176410.1021/es049453k ↗
25. Rácz · SAR QSAR Environ. Res. · 2018 · 29 · 66110.1080/1062936x.2018.1505778 ↗
26. Chicco · BioData Min. · 2021 · 14 · 1310.1186/s13040-021-00244-z ↗
27. A. Y.Ng , Feature selection, L1 vs. L2 regularization, and rotational invariance , in Proceedings of the twenty-first international conference on Machine learning , ICML ’04, Association for Computing Machinery , New York, NY, USA , 2004 , p. 78 10.1145/1015330.101543510.1145/1015330.1015435 ↗
28. K.He , X.Zhang , S.Ren and J.Sun , Deep Residual Learning for Image Recognition , in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2016 , pp. 770–778 10.1109/CVPR.2016.9010.1109/CVPR.2016.90 ↗
29. M.Tan and Q. V.Le , EfficientNetV2: Smaller Models and Faster Training . CoRR abs/2104.00298, 2021
30. J.Deng , et al. , ImageNet: A large-scale hierarchical image database , in 2009 IEEE Conference on Computer Vision and Pattern Recognition , 2009 , pp. 248–255 10.1109/CVPR.2009.520684810.1109/CVPR.2009.5206848 ↗
31. R. R.Selvaraju , et al. , via . CoRR abs/1610.02391, 2016
32. J. E.Cadotte , Interfacially synthesized reverse osmosis membrane , 1981
33. Gao · Environ. Sci. Technol. · 2021 · 56 · 257210.1021/acs.est.1c04373 ↗
34. Zunger · Nat. Rev. Chem. · 2018 · 2 · 012110.1038/s41570-018-0121 ↗
35. Kim · Sci. Adv. · 2020 · 6 · eaax932410.1126/sciadv.aax9324 ↗
36. Sattari · Soft Matter · 2021 · 17 · 760710.1039/d1sm00725d ↗
37. Lundberg · Nat. Mach. Intell. · 2020 · 2 · 5610.1038/s42256-019-0138-9 ↗
38. S.Ivanov and L.Prokhorenkova , Boost then Convolve: Gradient Boosting Meets Graph Neural Networks , arXiv , 2021 , preprint, arXiv:2101.08543 10.48550/arXiv.2101.0854310.48550/arXiv.2101.08543 ↗
39. Zhao · Nat. Synth. · 2023 · 2 · 50510.1038/s44160-023-00250-5 ↗
40. Caramelli · ACS Cent. Sci. · 2021 · 7 · 182110.1021/acscentsci.1c00435 ↗
41. Park · Matter · 2023 · 6 · 67710.1016/j.matt.2023.01.018 ↗
42. Noh · Matter · 2019 · 1 · 137010.1016/j.matt.2019.08.017 ↗
43. Liu · Sci. Adv. · 2020 · 6 · eabb318810.1126/sciadv.abb3188 ↗
44. Volokitina · J. Mater. Res. Technol. · 2024 · 31 · 298510.1016/j.jmrt.2024.07.038 ↗
45. Ma · J. Alloys Compd. · 2024 · 1007 · 17635210.1016/j.jallcom.2024.176352 ↗
46. Zhao · Theor. Chem. Acc. · 2007 · 120 · 21510.1007/s00214-007-0310-x ↗
47. Zhao · Acc. Chem. Res. · 2008 · 41 · 15710.1021/ar700111a ↗
48. Krishnan · J. Chem. Phys. · 1980 · 72 · 65010.1063/1.438955 ↗
49. Boys · Mol. Phys. · 1970 · 19 · 55310.1080/00268977000101561 ↗
50. Heid · J. Chem. Inf. Model. · 2023 · 64 · 910.1021/acs.jcim.3c01250 ↗
51. Yang · J. Chem. Inf. Model. · 2019 · 59 · 337010.1021/acs.jcim.9b00237 ↗
52. W.Jin , R.Barzilay and T.Jaakkola , Multi-Objective Molecule Generation using Interpretable Substructures , 2020
53. T.Chen and C.Guestrin , XGBoost: A Scalable Tree Boosting System , in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , KDD ’16 (ACM), 2016 10.1145/2939672.293978510.1145/2939672.2939785 ↗
54. G.Landrum , et al. , rdkit/rdkit: 2020_03_1 (Q1 2020) Release , 2020 10.5281/zenodo.373226210.5281/zenodo.3732262 ↗
55. Chicco · BioData Min. · 2023 · 16 · 410.1186/s13040-023-00322-4 ↗
56. T.Akiba , S.Sano , T.Yanase , T.Ohta and M.Koyama , Optuna: A Next-generation Hyperparameter Optimization Framework , 2019
57. Pedregosa · J. Mach. Learn. Res. · 2011 · 12 · 2825
58. V. N.Vapnik , The Support Vector method , Springer , Berlin Heidelberg , 1997 , p. 261–271 10.1007/bfb002016610.1007/bfb0020166 ↗