<![CDATA[Energy dissipation in stepped channels is an important parameter in the design of hydraulic structures because it affects flow efficiency, structural stability, and scour control in downstream areas. Energy loss is commonly estimated using empirical equations or hydraulic analyses, which often require considerable computational effort and time. Therefore, this study aims to develop a Machine Learning model to predict energy loss in stepped channels based on hydraulic parameters. The study utilized experimental data consisting of discharge, channel width, drop height, upstream flow depth, upstream flow velocity, Froude number, downstream flow depth, and downstream flow velocity as input variables, while energy loss was used as the output variable. The research methodology included data preprocessing, data splitting into 80% training data and 20% testing data, and model development using four Machine Learning algorithms, namely Artificial Neural Network (ANN), Support Vector Regression (SVR), Random Forest (RF), and Gradient Boosting (GB). Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). The results showed that the Gradient Boosting algorithm achieved the best performance, with an RMSE of 0.0214, an MAE of 0.0139, and an R² of 0.9372, indicating that the model explained approximately 93.72% of the variation in energy loss. The Actual versus Predicted Scatter Plot also demonstrated a high level of agreement between predicted and observed values. These findings indicate that the Gradient Boosting algorithm provides an accurate and efficient approach for predicting energy loss in stepped channels and has the potential to support the analysis, evaluation, and design of hydraulic structures.]]>
