Prediction of scour hole characteristics caused by water jets using metaheuristic artificial bee colony-optimized neural network and pre-processing techniques

Abstract Preventing plunge pool scouring in hydraulic structures is crucial engineering. Although many studies have been conducted experimentally to determine relationship between the scour depth and water jets several fields, available equations deficiencies calculating exact due complexity of process. This study investigated local using Metaheuristic Artificial Bee Colony-Optimized Feed Forward Neural Network (ABCFFNN), variational mode decomposition (VMD) ensemble empirical (EEMD) techniques. To set modeling, input parameters are impact angle, densimetric Froude number, impingement length, nozzle diameter. The models' training testing were data literature. performances compared with experiments. results demonstrate that depth, width, ridge height can be calculated more accurately than equations. A rank analysis was also applied obtain most critical parameter predicting jet scouring. ABC-FFNN, VMD-ABCFFNN EEMD-VMD-FFNN hybrid models performed parameters. As a result, ABC-FFNN algorithms produced best solution predict circular jets, values for (R2: 0.331 0.778) 0.495 0.863).