In-depth simulation of rainfall–runoff relationships using machine learning methods

Water Practice & Technology, Journal Year: 2024, Volume and Issue: 19(6), P. 2442 - 2459

Published: June 1, 2024

ABSTRACT Measurement inaccuracies and the absence of precise parameters value in conceptual analytical models pose challenges simulating rainfall–runoff modeling (RRM). Accurate prediction water resources, especially scarcity conditions, plays a distinctive pivotal role decision-making within resource management. The significance machine learning (MLMs) has become pronounced addressing these issues. In this context, forthcoming research endeavors to model RRM utilizing four MLMs: Support Vector Machine, Gene Expression Programming (GEP), Multilayer Perceptron, Multivariate Adaptive Regression Splines (MARS). simulation was conducted Malwathu Oya watershed, employing dataset comprising 4,765 daily observations spanning from July 18, 2005, September 30, 2018, gathered rainfall stations, Kappachichiya hydrometric station. Of all input combinations, incorporating Qt−1, Qt−2, R̄t identified as optimal configuration among considered alternatives. models' performance assessed through root mean square error (RMSE), average (MAE), coefficient determination (R2), developed discrepancy ratio (DDR). GEP emerged superior choice, with corresponding index values (RMSE, MAE, R2, DDRmax) (43.028, 9.991, 0.909, 0.736) during training process (40.561, 10.565, 0.832, 1.038) testing process.

Language: Английский

---

Scour depth prediction around bridge piers of various geometries using advanced machine learning and data augmentation techniques

Transportation Geotechnics, Journal Year: 2025, Volume and Issue: unknown, P. 101537 - 101537

Published: March 1, 2025

Language: Английский

---

In-depth simulation of netted collars on scour depth control using machine-learning models

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101820 - 101820

Published: Jan. 26, 2024

The present research aims to forecast the safeguarding efficacy of a mesh collar, hole diameter d, in developing scour depth around cylindrical bridge pier D under steady and clean water conditions utilizing three machine learning models (MLMs), namely Support Vector Machine (SVM), Gene Expression Programming (GEP), Multilayer Perceptron (MLP). A total 240 laboratory measured data were employed this study. experimental setup involved installation four distinct collars, configured shapes circle, square, rectangle, an d triangle by shape factor (SF) 1.78, 1, 2.3, 1.69, respectively. mean size non-cohesive sand particles was selected with particle 1.3 mm. Employing dimensional analysis, dimensionless parameters, SF, d/D, Uc/U identified as independent variables adopting for input MLMs. performance assessment metrics Root Mean Squared Error (RMSE), Absolute (MAE), coefficient determination (R2), Developed Discrepancy Ratio (DDR). simulation results demonstrated that MLMs exhibit high degree accuracy predicting relative (RSD) influenced presence collars. Among aforementioned models, GEP model its superiority corresponding values (RMSE, MAE, R2, DDRmax) indices (0.11342, 0.08642, 0.85058, 2.54) (0.0787, 0.0624, 0.8959, 3.66) during training testing phases, Finally, equation extracted predict RSD using model.

Language: Английский

---

Scouring and bed morphology dynamics in a sharp bend with collared pier under unsteady flow

Hydrological Sciences Journal, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 22

Published: Sept. 4, 2024

Language: Английский

---

Introducing high-order response surface method for improving scour depth prediction downstream of weirs

Applied Water Science, Journal Year: 2024, Volume and Issue: 14(6)

Published: May 5, 2024

Abstract Scour depth downstream of weirs is considered one the most important hydraulic problems, which greatly influences stability weirs. Recently, artificial intelligence (AI) methods have become increasingly popular in modeling variables, especially scour depth, because they can capture nonlinear relationships between input variables and their associated objectives. Despite importance, these models problems with hyperparameter tuning due to structures, so algorithms must be used tune hyperparameters. Moreover, are usually tuned by using trial-and-error method select hyperparameters such as number hidden nodes, transfer function, learning rate, this case, main problem overfitting during training phase. To solve high-order response surface (HORSM), an improved version (RSM), alternative approach for first time study predict depth. The HORSM model based on polynomial functions (from two six) compared neural network (ANN). findings indicate that fifth order function yields precise predictions, a higher coefficient determination ( R 2 ) 0.912 Willmott Index WI 0.972 values obtained ANN = 0.886 0.927). accuracy predictions represented reduction mean square error up 44.17 29.01% classical RSM ANN, respectively. suggested established excellent correlation experimental values.

Language: Английский

---

Analysing Bridge Pier Scour Depth Using Machine Learning: The Role of Slot Geometry

Published: Jan. 1, 2025

Language: Английский

---

Local scour around bridge abutments in vegetated beds under ice-covered flow conditions – An experimental study and mathematical assessment using machine learning methods

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133257 - 133257

Published: April 1, 2025

Language: Английский

---

Machine learning prediction of flow-induced scour depth around isolated pier comparing stand-alone and ensemble models

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 156, P. 111318 - 111318

Published: June 2, 2025

Language: Английский

---

Data-based models to investigate protective piles effects on the scour depth about oblong-shaped bridge pier

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102759 - 102759

Published: Aug. 23, 2024

Language: Английский

---

Predicting Equilibrium Scour Depth Around Non-Circular Bridge Piers with Shallow Foundations Using Hybrid Explainable Machine Learning Methods

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103492 - 103492

Published: Nov. 1, 2024

Language: Английский

---