Machine Learning Optimizer for Carbon Nanotube Dispersions Across 666 Formulations

666 carbon nanotube dispersions systematically vary 36 organic dispersants, 22 solvents, and two dispersion methods. The dataset, created by Hirokuni Jintoku and last updated in April 2026, quantifies dispersion quality (D_score) and structural integrity (I_G/I_D) to train an XGBoost model for prescreening formulations.

Use Cases

• Training ML models to predict CNT dispersibility based on molecular descriptors and solvent-dispersant similarity metrics.
• Screening formulation and processing conditions to reduce experimental trial-and-error in nanomaterial research.
• Analyzing the relationship between process intensity and CNT structural integrity (I_G/I_D).
• Identifying practically useful solvent- and process-constrained formulations for downstream manufacturing.

Strengths

• Systematically covers a combinatorial design space with 666 distinct dispersions.
• Includes two key quantitative metrics: D_score for dispersion quality and I_G/I_D for structural integrity.
• Model performance metrics are provided (R²=0.57 for D_score, R²=0.73 for I_G/I_D).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Limited quantitative accuracy was reported for dispersants outside the training set.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

figshare

Collection Method

Experimental investigation of CNT dispersions with systematic variations in composition and processing parameters.

Time Range

null

Freshness

Last updated 2026-04-09 17:37:32; freshness should be verified.

Geography

null