Fig. 5 | Scientific Reports

Fig. 5

From: Predictive optimization of curcumin nanocomposites using hybrid machine learning and physics informed modeling

Fig. 5

(a) Principal-component biplot of formulation parameters. Each point represents one nanocomposite; color scale indicates measured LE %. PC1 + PC2 = 78% variance, dominated by polymer ratio and surfactant concentration. (b) Response surface of predicted Loading Efficiency (LE %) as a function of particle size and zeta potential. The optimum region (80–200 nm, − 30 to − 50 mV) corresponds to maximum LE % and matches colloidal-stability predictions by DLVO theory.

Back to article page