Optimizing Ternary Preparation Parameters of Thin-Film Nanocomposite Membranes for Tailore

A dataset from figshare by Airan Hu, last updated in April 2026, containing parameters for optimizing thin-film nanocomposite nanofiltration membranes. The data supports an interpretable machine learning study aimed at tailoring membrane selectivity for water purification, with molecular weight cutoff as a key performance indicator. The dataset is 18.1 KB in size and is available in CSV format.

Use Cases

• Training predictive models for membrane molecular weight cutoff based on substrate, nanomaterial, and interfacial polymerization parameters.
• Applying SHAP analysis to identify critical preparation factors for achieving low MWCO and high mineral ion passage.
• Optimizing ternary fabrication parameters to design membranes for specific drinking water purification goals.
• Studying the complex interactions between substrate density, nanomaterial load, and monomer concentration on membrane performance.

Strengths

• Data is structured for machine learning applications, as indicated by the use of SHAP and interpretable ML in the study.
• The dataset is openly available under a CC-BY-NC-4.0 license, facilitating academic reuse.
• Focuses on a specific, industrially relevant challenge in membrane science for water treatment.

Limitations

• Row count is unknown, which may limit suitability assessment for model training.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 18.1 KB, indicating limited scope.

Provenance

Source

figshare

Collection Method

Likely contains experimental or simulated preparation parameters and performance metrics from membrane fabrication studies.

Time Range

null

Freshness

Last updated 2026-04-24 15:12:35; freshness should be verified.

Geography

null