Estimating incipient motion velocity of bed sediments using different data-driven methods

• Published in: Applied soft computing Vol. 69; pp. 165 - 176
• Main Authors: Zounemat-Kermani, Mohammad, Mahdavi Meymand, Amin, Ahmadipour, Mina
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2018
• Subjects: Genetic algorithm; Invasive weed optimization; k-fold cross-validation; Monte Carlo; Threshold velocity; Threshold velocity; k-fold cross-validation; Monte Carlo; Invasive weed optimization; Genetic algorithm
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2018.04.041

[Display omitted] •Data-driven methods (DDMs) are used to estimate the threshold velocity of sediment motion.•The obtained results indicate that the WaveNet model has better performance than the other methods.•The results indicate that the median diameter of the particles and relative density are the most important parameters affecting the threshold velocity.•Results of Monte Carlo method showed that the median diameter of grain size has the maximum effect on variations of the incipient motion. In the present research, the data-driven methods (DDMs), are used to estimate the threshold velocity of sediment motion. Results of the DDMs used in this research, including artificial neural networks (FFNN & RBNN), adaptive neuro-fuzzy inference system models (ANFIS, ANFIS-GA & ANFIS-IWO), and wavelet neural network (WaveNet), are compared with those of the mathematical models and experimental observations. The obtained results indicate that the WaveNet model with the Nash–Sutcliffe coefficient of 0.997 has better performance than the other methods. Moreover, in order to specify the relative importance of the input parameters for the uncertainty of the threshold velocity, sensitivity analysis is performed, the results of which indicate that the median diameter of the particles and relative density are the most important parameters affecting the threshold velocity, respectively. In addition, the Monte Carlo simulation is used to quantify the uncertainty of the threshold velocity of motion. The uncertainty is expressed using the coefficient of variation (CV). The highest amount of CV is related to the median diameter of grain size, therefore, this parameter has the maximum effect on variations of the incipient motion.