Machine Learning Based Prediction of Hydraulic Jump Lengths in Stilling Basins for Barrages and Low-Head Hydraulic Structures
Mehran University Research Journal of Engineering and Technology · 2026
DOI: 10.22581/0320 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mehran University Research Journal of Engineering and Technology, 2026. Verfasst von Abdul Rehman und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
A hydraulic-jump-type stilling basin is a popular choice for energy dissipation, where the high-velocity, supercritical flow from a dam spillway transitions into a low-velocity, subcritical flow. Stilling basins are designed such that the hydraulic jump forms within the basin, ensuring the safety of the downstream natural streambed. Thus, prediction of length of hydraulic jump is critical in deciding the basins dimensions. Experimental data on hydraulic jump type stilling basins under low inflow Froude number were collected from the literature. Six machine learning (ML) models were trained and tested using experimental data related to low inflow Froude number stilling basins. For each model, the feature importance score was calculated using a permutation-based method, which showed that the inflow Froude number (F1) and the sequent depth ratio (Y) were most significant features for prediction of the length of the hydraulic jump across all ML models. The evaluation of the models' performance indicated that the artificial neural network based model and CatBoost performed better, with higher coefficients of determination (from 0.85 to 0.93), lower error metrics, and a balanced distribution of errors during training, testing, and validation. Whereas Random Forest and AdaBoost based models showed least coefficient of determination (both having 0.84) at the model training stage. Support vector machine based model performed least at the testing stage with coefficient of determination of 0.54.
Zitieren
APA
Rehman, A., Rehman, H. U., & Khan, N. M. (2026). Machine Learning Based Prediction of Hydraulic Jump Lengths in Stilling Basins for Barrages and Low-Head Hydraulic Structures. Mehran University Research Journal of Engineering and Technology. https://doi.org/10.22581/0320
Vancouver
Rehman A, Rehman HU, Khan NM. Machine Learning Based Prediction of Hydraulic Jump Lengths in Stilling Basins for Barrages and Low-Head Hydraulic Structures. Mehran University Research Journal of Engineering and Technology. 2026. doi:10.22581/0320
BibTeX
@article{Rehman2026,
author = {Rehman, Abdul and Rehman, Habib ur and Khan, Noor Muhammad},
title = {Machine Learning Based Prediction of Hydraulic Jump Lengths in Stilling Basins for Barrages and Low-Head Hydraulic Structures},
journal = {Mehran University Research Journal of Engineering and Technology},
year = {2026},
doi = {10.22581/0320}
}
EUVIMED