Application of AI-Based Techniques on Moody’s Diagram for Predicting Friction Factor in Pipe Flow

The friction factor is a widely used parameter in characterizing flow resistance in pipes and open channels. Recently, the application of machine learning and artificial intelligence (AI) has found several applications in water resource engineering. With this in view, the application of artificial intelligence techniques on Moody’s diagram for predicting the friction factor in pipe flow for both transition and turbulent flow regions has been considered in the present study. Various AI methods, like Random Forest (RF), Random Tree (RT), Support Vector Machine (SVM), M5 tree (M5), M5Rules, and REPTree models, are applied to predict the friction factor. While performing the statistical analysis (root-mean-square error (RMSE), mean absolute error (MAE), squared correlation coefficient (R 2 ), and Nash–Sutcliffe efficiency (NSE)), it was revealed that the predictions made by the Random Forest model were the most reliable when compared to other AI tools. The main objective of this study was to highlight the limitations of artificial intelligence (AI) techniques when attempting to effectively capture the characteristics and patterns of the friction curve in certain regions of turbulent flow. To further substantiate this behavior, the conventional algebraic equation was used as a benchmark to test how well the current AI tools work. The friction factor estimates using the algebraic equation were found to be even more accurate than the Random Forest model, within a relative error of ≤±1%, in those regions where the AI models failed to capture the nature and variation in the friction factor.