Developing improved machine learning methods to predict the flow characteristics through vertical and horizontal transitions in open channels

Abstract

Transitions in an open channel refer to the change in flow behavior due to changes in the channel geometry. Determining flow characteristics through transitions is an important topic as it is necessary to guarantee the ideal hydraulic performance of water structures with low costs. This research focuses on the flow characteristics through vertical and horizontal transitions through experimental study and then utilizing machine learning to predict the flow characteristics. The proposed framework aims to develop both the cascade-forward artificial neural network (CFANN) model and the regression model to enhance the prediction of flow characteristics. The first model developed modifies the CFANN using dandelion optimizer (DO) to determine the ideal CFANN configuration. The second model used gene expression programming to develop statistical equations. The obtained CFANN–DO model has proven high accuracy in predicting the flow rates at various water loads and speeds achieving a coefficient of determination of approximately 100% for training data and 99.5% for testing data. Finally, predicting the characteristics of vertical and horizontal transitions in open channels is a critical issue. Manipulating these transitions can create a habitat for aquatic organisms, reduce erosion, and improve the overall environment.