Table 1 Performance comparison of optimized machine learning models.

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

Model

Target

R2

RMSE

MAE

Gradient Boosting Regressor

LE%

0.89

6.24

4.87

Random Forest

LE%

0.84

7.89

6.12

SVR

LE%

0.76

9.45

7.53

Gradient Boosting Regressor

EE%

0.87

7.15

5.42

Physics-Informed NN

EE%

0.83

8.10

6.25

XGBoost

EE%

0.85

7.52

5.78