Prediction of maximum scour depth downstream of bed sills using integrated machine learning algorithms

Accurate prediction of maximum relative scour depth (ys/Hs) is critical for hydraulic infrastructure resilience. This study advances scour depth prediction downstream of bed sills by establishing three ensemble models—Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and XGBoost—trained on...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Environmental modelling & software : with environment data news Ročník 192; s. 106548
Hlavní autori: Guan, Dawei, Li, Zhanchen, Zheng, Haoran, Hong, Jian-Hao, Fazeres-Ferradosa, Tiago, Asumadu, Richard
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.08.2025
Predmet:
Bed sills
Empirical formulas
Integration algorithm
Scour depth
Weir-like structures
Integration algorithm
Empirical formulas
Weir-like structures
Scour depth
Bed sills
ISSN:1364-8152
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Accurate prediction of maximum relative scour depth (ys/Hs) is critical for hydraulic infrastructure resilience. This study advances scour depth prediction downstream of bed sills by establishing three ensemble models—Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and XGBoost—trained on a comprehensive dataset combining 328 standardized flume experiments (clear-water and live-bed conditions) with 73 field measurements. Validation using 29 field datasets from Maso River reveals MAE reductions of 32.5 %, 28.7 %, and 30.2 % for RF, GBDT, and XGBoost, respectively, compared to laboratory-trained models, translating to at least 31.6 % higher accuracy than traditional empirical approaches. Comprehensive sensitivity analysis identifies four dimensionless parameters as critical predictors, ranked by their relative importance to scour development: morphological transition coefficient (a1/Hs) > sediment sorting coefficient (a1/ΔD95) > weir spacing ratio (L/Hs) > channel slope (S0). By integrating lab and field data, this approach enhances scour prediction accuracy for fluvial risk management. •Combines 328 flume experiments and 73 field measurements, overcoming scale limitations of traditional empirical methods.•Morphological transition coefficient (a1/Hs) most influential, then sediment sorting (a1/ΔD95), weir spacing (L/Hs), slope (S0).•Ensemble (RF/GBDT/XGBoost) achieves R²=0.82, 36.6% lower RMSE vs empirical formulas, validated lab and field.
ISSN:1364-8152
DOI:10.1016/j.envsoft.2025.106548