Learning the Path to Ion Separation: A Proof-of-Concept for Machine Learning-Assisted Inverse Design (MLAID) of Nanofiltration Membranes
- 1School of Civil & Environmental Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
Abstract
Advancing the design of polymeric membranes through material screening and discovery offers a powerful strategy to guide future membrane fabrication tailored to a wide range of separation challenges. Traditional trial-and-error methods often fall short in navigating this large monomer and process-design space, whereas machine learning-assisted inverse design (MLAID) can provide an extensible workflow for translating literature-derived membrane knowledge into ranked experimental candidates. Building on prior inverse-design strategies that combine machine learning (ML) with Bayesian optimization (BO), this study applies MLAID to prioritize membrane candidates within a target-defined nanofiltration (NF) design space. MLAID models are trained with membrane fabrication data, and their underlying patterns are interpreted through Shapley additive explanations (SHAP). SHAP was used to investigate model-attribution patterns, and BO was used to prioritize monomer and fabrication-condition combinations for producing polyamide membranes with targeted permeability and selectivity. The MLAID framework prioritized candidate formulations across target salt-water permeabilities of 4 to 12 LMH/bar (L m–2 h–1 bar–1), with Na2SO4 rejection used as the experimental benchmark. Fabrication and testing served as the experimental decision gate for evaluating the model-prioritized candidates. Overall, this study demonstrates how ML/BO-guided prioritization can accelerate identification of promising monomers and fabrication conditions within an encoded design space, while providing a workflow backbone that can expand as richer target-specific data sets, descriptors, and validation become available.
Related
- Tailored Graphene Oxide Incorporated PES/CA Mixed‐Matrix Loose Nanofiltration Membranes for Water Softening and Divalent Salt Removal
- Coupling ceramic nanofiltration membranes with catalytic ozonation for fouling control during treatment of secondary urban wastewater effluent
- CMC-based nanofiltration membranes for treatment of dye-contaminated wastewater.
- Zwitterionic poly (amino acid methacrylate) brushes functionalized dendritic mesoporous silica nanoparticles in layer-by-layer assembled membranes for selective Ion separation
- Polysulfone mixed matrix membranes embedded with sub-25 nm NH2-MIL-101(Cr) for enhanced divalent salt separation and permeability
BibTeX
@article{jeong2026learning,
title = {{Learning the Path to Ion Separation: A Proof-of-Concept for Machine Learning-Assisted Inverse Design (MLAID) of Nanofiltration Membranes}},
author = {Nohyeong Jeong and Elif Demirel and Changyoon Jun and Yongsheng Chen},
journal = {Environmental Science \& Technology},
year = {2026},
month = sep,
doi = {10.1021/acs.est.5c15241},
url = {https://doi.org/10.1021/acs.est.5c15241},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Learning the Path to Ion Separation: A Proof-of-Concept for Machine Learning-Assisted Inverse Design (MLAID) of Nanofiltration Membranes
AU - Nohyeong Jeong
AU - Elif Demirel
AU - Changyoon Jun
AU - Yongsheng Chen
PY - 2026
DA - 2026/09/29
JO - Environmental Science & Technology
DO - 10.1021/acs.est.5c15241
UR - https://doi.org/10.1021/acs.est.5c15241
AB - Advancing the design of polymeric membranes through material screening and discovery offers a powerful strategy to guide future membrane fabrication tailored to a wide range of separation challenges. Traditional trial-and-error methods often fall short in navigating this large monomer and process-design space, whereas machine learning-assisted inverse design (MLAID) can provide an extensible workflow for translating literature-derived membrane knowledge into ranked experimental candidates. Building on prior inverse-design strategies that combine machine learning (ML) with Bayesian optimization (BO), this study applies MLAID to prioritize membrane candidates within a target-defined nanofiltration (NF) design space. MLAID models are trained with membrane fabrication data, and their underlying patterns are interpreted through Shapley additive explanations (SHAP). SHAP was used to investigate model-attribution patterns, and BO was used to prioritize monomer and fabrication-condition combinations for producing polyamide membranes with targeted permeability and selectivity. The MLAID framework prioritized candidate formulations across target salt-water permeabilities of 4 to 12 LMH/bar (L m–2 h–1 bar–1), with Na2SO4 rejection used as the experimental benchmark. Fabrication and testing served as the experimental decision gate for evaluating the model-prioritized candidates. Overall, this study demonstrates how ML/BO-guided prioritization can accelerate identification of promising monomers and fabrication conditions within an encoded design space, while providing a workflow backbone that can expand as richer target-specific data sets, descriptors, and validation become available.
SN - 0013-936X
SN - 1520-5851
ER -