Hybrid model of support vector regression and fruitfly optimization algorithm for predicting ski-jump spillway scour geometry

Accurate prediction of the scour hole depth and dimensions downstream ski-jump spillways has been an important issue among hydraulic researchers for decades. In recent years, computing methods such as Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference Systems (ANFISs) Support Vector Regression (SVR) have shown a powerful performance in characteristics owing to their flexibility learning nature. present paper, new hybrid approach proposed first time order improve estimation power SVR tool geometry below spillways. The principal pattern equilibrium phase predicted using optimized with Fruitfly Optimization Algorithms (FOAs). model is compared corresponding simple model. To evaluate further, it also other machine empirical methods, ANNs, ANFISs regression equations. results show that SVR-FOA method performs well, improves remarkably on Machines (SVMs) results, estimates geometrical parameters more accurately than model, can be applied alternative reliable scheme estimations which demonstrate shortcomings. precision level by about 8% SVM terms correlation coefficient.