Table 3 Summarizes the performance of the machine learning models—RF and XGBoost —in predicting DO using all input parameters.

From: A hybrid framework of feature selection and interpretability for dissolved oxygen prediction in drinking water treatment plants

Evaluation Metric

R²

MSE

MAE

RMSE

EVS

Unit

-

(mg/L)2

(mg/L)

(mg/L)

-

RF

0.928

0.073

0.194

0.271

0.928

XGBoost

0.942

0.059

0.172

0. 244

0.942