Accurate prediction of the relative length of a hydraulic jump (Lj/d1) is essential for the safe and economical design of energy dissipation structures in open channels. In rough sloping channels, this prediction becomes challenging due to strong nonlinear interactions among inflow Froude number (Fr1), bed roughness height (h), and channel slope (θ), which are inadequately represented by conventional empirical equations. The objective of this research is to develop robust ML models for predicting Lj/d1 under combined rough and sloping bed situation and to find the most efficient modeling approach. The study utilized 452 experimental data consisting extensive range of Fr1 (2.49 to 7.62), h (0 to 30 mm), θ (0° to 6°). Four ML models such as ANN, RF, AdaBoost, and CatBoost were trained using 70% of the experimental data and tested on the remaining 30%. Model effectiveness was analyzed through graphical assessment, statistical evaluation, rank analysis, and SHapley Additive exPlanations based sensitivity analysis. Results demonstrated that all models attain high predictive accuracy; however, CatBoost performs better than others with excellent generalization, obtaining R² values of 0.9998 and 0.9952, MARE values of 0.0047 and 0.0201 during training and testing of experimental data, respectively. SHAP analysis validates Fr1 as the predominant parameter, followed by surface roughness and bed slope. The novelty of this research lies in the integrated application and comparison of multiple ML techniques, particularly CatBoost, for predicting hydraulic jump length in the combined rough sloping scenario, providing an accurate, interpretable, and practical framework for hydraulic engineering applications.
The proposed AFELA–machine learning framework provides a computationally efficient, reliable, and interpretable approach for tunnel stability assessment in sloping rock mass conditions.
A. Kumar, V. Chauhan, Aayush Kumar et al.· Transportation Infrastructur...· 1 citation
The current study combines numerical modelling and machine learning to identify the stability of applications in nail reinforced slope study. PLAXIS LE was used to develop different slopes having different soil properties including various values for cohesion (5, 10, 15 kPa), angle of internal friction (20°, 25°, 30°), unit weight (17, 18, 19 N/m³), and slope angle (30°, 35°, 40°, 45°, 50°, 60°, 70°). Safety Factors (FOS) prediction models such as Random Forest (RF), Linear Regression (LR), and K-Nearest Neighbors (KNN) have been developed using the parameters included in the study. The Random Forest model has shown a superior performance among the other models with the lowest Mean Absolute Error (MAE: 0.053) and Mean Squared Error (MSE: 0.006), taking into consideration the highest value of R² (0.957) and Adjusted R² (0.951) to indicate a better predictive accuracy. With R² values of 0.903 and 0.920, respectively, Linear Regression and KNN also showed considerable strength of results. The results mentioned above show the bright future of machine learning models with Random Forest in predicting slope stability and contribute to refining nail reinforcement strategies. It shall also provide an input for developing cost-effective and robust slope rehabilitation measures in a geotechnically unfriendly environment.
The potential effectiveness of the proposed robustness-oriented evaluation framework for ML-assisted Ra prediction under limited-data machining conditions is supported, and ELM achieved the highest prediction accuracy.
Phong Thanh Huynh, T. Nguyen, H. Thuong· Engineering Research Express· 0 citations
Manning's roughness coefficient (n) is crucial for reliable hydraulic analysis of natural and artificial open channels. This paper presents a state-of-the-art work on principles of flow resistance mechanisms of natural channels and n estimation approaches. Furthermore, it reviews classical empirically driven approaches, such as Strickler, Cowan, Meyer–Peter and Müller, Limerinos, and Henderson, as well as tabulated, photographic, and storage-based techniques. The latter is a consideration in terms of formulations that factor into vegetation effects, bed material characteristics, bedform-induced resistance, and composite channel roughness. Newer advances in entropy theory, statistical approaches, and data-driven methods are also introduced. The study describes both the advantages and disadvantages of specific methods and shows that no way to predict Manning’s n can be applied universally under different flow conditions and channel types. Instead, the precise estimation has to be based on empirical field observations, analytical construction, and engineering judgment. The observations support the use of an integrated and hybrid approach and can be supplemented with high-resolution measurements and standardized databases for the purpose of minimizing prediction uncertainty for the roughness estimation. This review contributes to enhancing the knowledge and application base of researchers and practitioners in river hydraulics, channel design, and flood modeling.
A. Nama, Sabah Jassim Mohammed, Sura Sabah Rasool et al.· Jurnal Engineering· 0 citations
The accurate prediction of hydrodynamic characteristics and structural responses in underwater fishing gear is critical for optimizing design, ensuring operational safety, and minimizing environmental impact. To overcome the computational costs and scalability limitations of traditional physical modeling, this study evaluates three machine learning algorithms such as Random Forest (RF), Light Gradient Boosting Machine (LightGBM), and Support Vector Machine with a Radial Basis Function kernel (SVM-RBF) to predict the hydrodynamic coefficients and structural responses of tuna longline components, including mainlines and branch lines. Models were trained and validated using a comprehensive flume tank dataset encompassing six gear configurations tested across varying flow velocities and lead-line weights. Results demonstrate that optimal model selection is inherently task dependent. For hydrodynamic coefficients, LightGBM achieved superior predictive accuracy for branch-line drag (whole-dataset R2 = 0.8315), while both LightGBM and SVM-RBF excelled in lift prediction. Conversely, structural responses (sinking depth and x-displacement) proved inherently more difficult to model deterministically due to high-frequency transient dynamics and stochastic variability. While LightGBM provided balanced generalization for sinking depth, SVM-RBF exhibited severe overfitting for x-displacement. In contrast, RF maintained the most conservative and consistent performance across structural targets, effectively mitigating the memorization of dynamic noise observed in the more complex algorithms. Beyond predictive modeling, feature importance analysis identified flow velocity, lead-line weight, material stiffness, and geometric parameters as dominant physical drivers, validating the physical plausibility of the models. Crucially, the integration of experimental and ML analyses revealed that a polylactic acid (PLA)-integrated midsection configuration consistently yielded the lowest and most stable drag force (0.004–0.13 N at 0.49 m/s), representing a 30–60% reduction compared to conventional nylon lines. Furthermore, the study uncovered novel physical phenomena, including velocity-independent deformation stability, progressive transient sinking kinetics, and tension-induced load redistribution. These findings establish machine learning as a reliable, scalable surrogate for longline gear design, advocating for thin-diameter, biodegradable PLA-integrated lines to enhance hydrodynamic efficiency and mitigate marine plastic pollution, while underscoring the necessity of task-specific algorithm selection for robust engineering applications.
Abdulai Jalloh, Thierry Bruno Nyatchouba Nsangue, Liming Song et al.· Fishes· 0 citations
