Table 1_Machine learning and mathematical modeling for comparative analysis of green-synth

A 2026 study by Yusuf Şavşatlı compares the effects of green-synthesized, chemically synthesized, and bulk zinc oxide nanoparticles on linseed crop traits. The dataset likely contains results from field experiments where seeds were primed with different nanoparticle types at concentrations of 25, 50, and 75 ppm for 1, 2, and 4 hours, with agronomic traits analyzed using ANOVA, response surface methodology, and machine learning models including KNN, Random Forest, and XGBoost.

Use Cases

• Compare the efficacy of biogenic versus chemical nanoparticles based on the described experimental treatments.
• Model nonlinear, hormetic dose-response relationships in crop traits based on nanoparticle concentration and exposure time.
• Train regression models to predict linseed agronomic performance based on seed priming parameters.
• Identify key factors influencing crop yield using feature analysis from the described machine learning models.

Strengths

• Dataset is associated with a study employing seven machine learning models (KNN, RF, Extra Trees, SVR, XGBoost, CatBoost, MLP) for analysis.
• Experimental design includes three nanoparticle types, three concentrations, and three exposure durations, suggesting a structured factorial design.
• Results are validated under field conditions, indicating real-world applicability.

Limitations

• Dataset size is very small at 31.8 KB, suggesting limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Yusuf Şavşatlı

Collection Method

Field experiments on linseed cultivar 'Yılmaz' with seed priming treatments.

Freshness

Last updated 2026-05-11 04:26:54; freshness should be verified.