🔬 Research-Grade ML Tool  ·  Abelmoschus esculentus

OkraML Predictor

Predict material properties of okra-derived systems across corrosion inhibition, pollutant adsorption, biopolymer composites, and supercapacitor electrochemistry using a Heterogeneous Voting Ensemble ML model.

231Experimental Runs
5Application Domains
57Literature Sources
🌿
Application Domains

Five Functional Areas of Okra-Derived Materials

Each domain is modeled with a Heterogeneous Voting Ensemble (Random Forest + Gradient Boosting + Extra Trees), trained on MICE-imputed experimental data.

⚗️
Corrosion Inhibition

Steel Protection

Predict inhibition efficiency (%) of okra extract and graft polymer inhibitors in HCl medium. Icorr dominates prediction.

0.8422

Target: Inhibition_Efficiency_percent (0–97%)

💧
Adsorption / Pollutant Removal

Contaminant Uptake

Predict adsorption capacity qe (mg/g) for heavy metals, dyes and microplastics. Thermodynamic ΔH is the top SHAP driver.

0.8987

Target: Adsorption_Capacity_qe_mg_g (log scale)

🧵
Biopolymers & Composites

Mechanical Performance

Predict tensile strength (MPa) of okra-fiber reinforced polymers. Secondary reinforcement content drives performance.

0.5744

Target: Tensile_Strength_MPa (22–50 MPa)

Electrochemistry / Carbon

Supercapacitor

Predict specific capacitance (F/g) of okra-derived activated carbons. Current density and configuration are top SHAP features.

0.8951

Target: Specific_Capacitance_F_g (121–318 F/g)

🔴
Nanoparticle Synthesis

Green Synthesis Limited

Green synthesis of nanoparticles from okra. Model R² is negative, indicating high variability and insufficient data for reliable prediction.

−0.5268

Target: Inhibition_Zone_Diameter_mm — Predictor excluded

Open the Prediction Tool →
Methodology Overview

How the Models Were Built

🧮 MICE Imputation

Missing experimental values were handled using Multivariate Imputation by Chained Equations (MICE), preserving inter-feature correlations across all five domains. Imputation improved dataset completeness without introducing uniform bias.

🌲 Heterogeneous Voting Ensemble

Three tree-based algorithms — Random Forest, Gradient Boosting, and Extra Trees — were trained independently per domain and combined via soft voting. This ensemble consistently outperformed individual models, particularly for adsorption (R²=0.8987) and electrochemistry (R²=0.8951).

📊 SHAP Explainability

SHapley Additive exPlanations (SHAP) decomposed each prediction into feature contributions. Key findings: corrosion current density (Icorr) is the dominant corrosion predictor; thermodynamic ΔH drives adsorption capacity; current density governs supercapacitor performance.

🔁 Cross-Validation

All R² and error metrics reported are from 5-fold stratified cross-validation, ensuring unbiased performance estimates for small experimental datasets (n = 6–67 per domain after imputation).

Full Methodology Details →
Model Performance

Cross-Validation Results — All Domains & Models

5-fold CV metrics. Bold ensemble rows represent the deployed predictor. R² values represent explained variance; MAE and RMSE are in target units (IE%, log(mg/g+1), MPa, F/g).

Domain Model CV R² CV MAE CV RMSE
Corrosion InhibitionRandom Forest0.84245.36410.859
Gradient Boosting0.82265.30911.521
Extra Trees0.84084.75910.912
🏆 Heterogeneous Voting0.84224.91110.865
Adsorption / Pollutant RemovalRandom Forest0.87740.3500.468
Gradient Boosting0.88410.3010.455
Extra Trees0.86910.3210.484
🏆 Heterogeneous Voting0.89870.2830.426
Biopolymers & CompositesRandom Forest0.55912.8804.113
Gradient Boosting0.57352.9064.046
Extra Trees0.53602.9954.220
🏆 Heterogeneous Voting0.57442.9154.041
Electrochemistry / CarbonRandom Forest0.814612.23117.598
Gradient Boosting0.869310.12314.772
Extra Trees0.829010.75416.897
🏆 Heterogeneous Voting0.89518.97413.234
Nanoparticle Green SynthesisRandom Forest−0.19991.1782.017
Gradient Boosting−0.80281.4302.472
Extra Trees−0.75251.4122.438
Heterogeneous Voting−0.52681.2922.275

Ready to make a prediction?

Enter your experimental conditions across corrosion, adsorption, composites, or electrochemistry and receive an instant ML-based estimate with SHAP-guided insights.

Open Prediction Tool → Citation & Dataset Info