Machine learning approaches for adequate prediction of flow resistance in alluvial channels with bedforms

Abstract

In natural rivers, flow conditions are mainly dependent on flow resistance and type of roughness. The interactions among flow and bedforms are complex in nature as bedform dynamics primarily regulate the flow resistance. Manning's equation is the most frequently used equation for this purpose. Therefore, there is a need to develop alternate reliable techniques for adequate prediction of Manning's roughness coefficient (n) in alluvial channels with bedforms. Thus, the main objective of this study is to utilize machine learning (ML) models for predicting ‘n’ based on the six input features. The performance of ML models was assessed using Pearson's coefficient (R2), sensitivity analysis, Taylor's diagram, box plots, and K-fold method has been used for the cross-validation. Based on the output of the current work, models such as random forest, extra trees regression, and extreme gradient boosting performed extremely well (R2 ≥ 0.99), whereas, Lasso Regression models showed moderate efficiency in predicting roughness. The sensitivity analysis indicated that the energy grade line has a significant impact in predicting the roughness as compared to the other parameters. The alternate approach utilized in the present study provides insights into riverbed characteristics, enhancing the understanding of the complex relationship between roughness and other independent parameters. HIGHLIGHTS This study focuses on accurately predicting n in alluvial channels with bedforms.; The intricate interplay between flowing water and bedforms adds complexity to flow resistance prediction.; A significant observation is that integrating all input parameters results in enhanced accuracy when predicting flow resistance.; Leveraging modern techniques, the study employs four machine learning models, to predict n.;

Keywords

• alluvial channels
• bedforms
• friction factor
• machine learning
• roughness