We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Boosting ensembles for estimation of discharge coefficient and through flow discharge in broad-crested gabion weirs
Summary
Researchers evaluated machine learning models — including Gradient Boosting, XGBoost, and CatBoost — for predicting hydraulic performance of gabion weirs, finding that boosting ensemble methods accurately estimated discharge coefficients for these environmentally friendly water management structures.
Abstract Gabion weirs are environment-friendly structures widely used for irrigation and drainage network purposes. These structures' hydraulic performance is fundamentally different from solid weirs' due to their porosity and the existence of a through-flow discharge. This paper investigates the reliability and suitability of a number of Machine learning models for estimation of hydraulic performance of gabion weirs. Generally, three different Boosting ensemble models, including Gradient Boosting, XGBoost, and CatBoost, are compared to the well-known Random Forest and a Stacked Regression model, with respect to their accuracy in prediction of the discharge coefficient and through-flow discharge ratio of gabion weirs in free flow conditions. The Bayesian optimization approach is used to fine-tune model hyper-parameters automatically. Recursive feature elimination analysis is also performed to find optimum combination of features for each model. Results indicate that the CatBoost model has outperformed other models in terms of estimating the through flow discharge ratio ( Q in /Q t ) with R 2 = 0.982, while both XGBoost and CatBoost models have shown close performance in terms of estimating the discharge coefficient ( C d ) with R 2 of CatBoost equal to 0.994 and R 2 of XGBoost equal to 0.992. Weakest results were also produced by Decision tree regressor with R 2 = 0.821 and 0.865 for estimation of C d and Q in /Qt values.
Sign in to start a discussion.
More Papers Like This
Predicting microplastic transport in open channels with different bed types and river regulation with machine learning techniques
Researchers studied microplastic transport in open channel flows with different bed types (acrylic, sand, cobble) and river regulation structures (weirs, sluice gates) using laboratory flumes. Sluice gates retained fewer microplastics than weirs, and machine learning models outperformed traditional bivariate analysis for predicting retention across conditions.
Integration of High-Accuracy Geospatial Data and Machine Learning Approaches for Soil Erosion Susceptibility Mapping in the Mediterranean Region: A Case Study of the Macta Basin, Algeria
Researchers compared four machine learning models for mapping soil erosion susceptibility in northern Algeria, finding that categorical boosting (CatBoost) outperformed other approaches in predicting erosion risk in Mediterranean agricultural landscapes.
Applicability of machine learning techniques to analyze Microplastic transportation in open channels with different hydro-environmental factors
Researchers applied machine learning models to predict how microplastics move through open water channels under different flow conditions, vegetation patterns, and particle densities. They found that tree-based algorithms like Random Forest and Extreme Gradient Boost significantly outperformed traditional statistical models in prediction accuracy. The study demonstrates that machine learning can be a valuable tool for understanding and forecasting microplastic transport in waterways.
An Efficient Data Driven-Based Model for Prediction of the Total Sediment Load in Rivers
A data-driven machine learning model was developed to predict total sediment load in rivers using readily available hydrological and morphological variables, outperforming conventional empirical sediment transport equations in accuracy. The model provides a practical tool for river management applications where comprehensive physical measurements are unavailable.
Using machine learning models to predict the effects of seasonal fluxes on Plesiomonas shigelloides population density
Researchers applied 15 machine learning algorithms to predict how seasonal environmental changes affect the population density of Plesiomonas shigelloides bacteria in river water, finding that extreme gradient boosting (XGB) outperformed other models and that temperature and suspended solids were the strongest predictors.