Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated just now
PreprintCC BYChemRxiv

Data-Driven Prospective Design of Phase-Inversion Conductive Polymer Membranes

  • Jinyu Liu1,2
  • Jiayue Hu3,2
  • Zefang Huang1,2
  • Bingxin Li1,2
  • Ling Liu3,2
  • Heyang Yuan1,2
  1. 1Department of Civil and Environmental Engineering
  2. 2Temple University
  3. 3Department of Mechanical Engineering
Open at sourcePDFDOICite

Abstract

Conductive polymer membranes combine separation and electrical functionality, but their design remains challenging because performance emerges from coupled effects of composition, fabrication, and operating conditions. Here, we assembled 396 membrane records from 77 publications and developed target-specific machine-learning models for pure-water permeability (PWP), solute rejection, and electrical conductivity. Weighted artificial neural network ensembles for PWP and rejection and XGBoost for conductivity achieved fixed-holdout R2 values of 0.855, 0.896, and 0.914, respectively, with distinct SHAP feature-contribution patterns across the three targets. We then coupled the predictive models with residual Gaussian-process uncertainty estimation and sequential Monte Carlo expected hypervolume improvement to search a 3,024-member PANI–DBSA/PES design space and identify 12 formulations for prospective experimental evaluation. Atomistic molecular dynamics simulations provided complementary mechanistic insight: increasing PANI from 0.47 to 1.89 wt% decreased the first-shell hydration number around DBSA sulfonate sites from 1.02 to 0.74, while the apparent finite-time water diffusion coefficient declined from 0.6910-10 m2∙s-1 in neat PES to 0.3710-10 m2∙s-1 at 1.89 wt% PANI. Together, these results connect literature-derived learning, uncertainty-aware formulation selection, and molecular-scale interpretation, providing a systematic framework for prospective conductive membrane design

Related

  1. Effect of the Reduction Degree of Graphene Oxide on the Cyclization of Polyacrylonitrile in PAN/GO Composite Membranes Prepared by Phase Inversion.
    Ryszard Fryczkowski, Beata Fryczkowska
    MembranesPeer-reviewedCC BYFull textHydrology & soilsEurope PMC
  2. Polymer-modified MXene thin-film nanocomposite membranes for forward osmosis
    Aidin Bashardoust, Prokopios Georgopanos, Alireza Shakeri
    Scientific ReportsPeer-reviewedCC BY 4.0Full textHydrology & soilsCrossref
  3. Structure-Driven Inversion: A New Paradigm for Solving Inverse Problems
    Shengchang Chen
    arXivPreprintCC BY-NC-SA 4.0Full textGeophysics & seismologyNumerical analysis & scientific computingarXiv
  4. PSDWII: Physical-Structure-Driven Waveform Inversion Imaging
    Shengchang Chen
    arXivPreprintCC BY-NC-SA 4.0Full textGeophysics & seismologyarXiv
  5. Conductive Alginate–Carbon-Black Bioanode for Immediate Microbial Electrolysis Cell Operation
    Abhishiktha Chiliveru, Vamshi Krishna Bommagani, Avinash Jukanti +3
    PolymersPeer-reviewedCC BYFull textEnvironmental science & pollutionEurope PMCCrossref

Cite

BibTeXRIS
BibTeX
@misc{liu2026datadriven,
  title = {{Data-Driven Prospective Design of Phase-Inversion Conductive Polymer Membranes}},
  author = {Jinyu Liu and Jiayue Hu and Zefang Huang and Bingxin Li and Ling Liu and Heyang Yuan},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15010034/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010034/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - Data-Driven Prospective Design of Phase-Inversion Conductive Polymer Membranes
AU  - Jinyu Liu
AU  - Jiayue Hu
AU  - Zefang Huang
AU  - Bingxin Li
AU  - Ling Liu
AU  - Heyang Yuan
PY  - 2026
DA  - 2026/10/07
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15010034/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010034/v1
AB  - Conductive polymer membranes combine separation and electrical functionality, but their design remains challenging because performance emerges from coupled effects of composition, fabrication, and operating conditions. Here, we assembled 396 membrane records from 77 publications and developed target-specific machine-learning models for pure-water permeability (PWP), solute rejection, and electrical conductivity. Weighted artificial neural network ensembles for PWP and rejection and XGBoost for conductivity achieved fixed-holdout R2 values of 0.855, 0.896, and 0.914, respectively, with distinct SHAP feature-contribution patterns across the three targets. We then coupled the predictive models with residual Gaussian-process uncertainty estimation and sequential Monte Carlo expected hypervolume improvement to search a 3,024-member PANI–DBSA/PES design space and identify 12 formulations for prospective experimental evaluation. Atomistic molecular dynamics simulations provided complementary mechanistic insight: increasing PANI from 0.47 to 1.89 wt% decreased the first-shell hydration number around DBSA sulfonate sites from 1.02 to 0.74, while the apparent finite-time water diffusion coefficient declined from 0.6910-10 m2∙s-1 in neat PES to 0.3710-10 m2∙s-1 at 1.89 wt% PANI. Together, these results connect literature-derived learning, uncertainty-aware formulation selection, and molecular-scale interpretation, providing a systematic framework for prospective conductive membrane design
ER  -