A Wavelet-ANFIS Model to Estimate Sedimentation in Dam Reservoir

Abstract

An accurate prediction of sedimentation in dam reservoir is a challenging issue due to the complex and non-linear physics of the problem. Anyhow, soft-computing-based techniques showed great ability for predicting non-linear phenomena and have been used for different purposes. The main objective of this study is to estimate the volume of sedimentation in Karaj dam using a wavelet-ANFIS (WANFIS) and a wavelet-neural network (WANN) model. Monthly average flow is used to estimate monthly averaged suspended sediment load for a thirty-year period. The amount of bed load is computed based on the suspended sediment load and the river slope and the total volume of sedimentation in the reservoir is calculated with subtracting the upstream (Karaj River) and downstream (Beylaghan River) total sediment load. In WANFIS and WANN models, monthly average flow time series are decomposed to several sub-time series using different wavelet decomposition levels. The total volume of sedimentation in Karaj dam obtained from different techniques such as WANFIS, WANN, ANFIS, ANN and hydrography are compared together. The comparison demonstrates that WANFIS model is superior to the other techniques. For WANFIS and WANN models, the best model is obtained by two and three wavelet decomposition levels respectively. Findings of this study reveal that Wavelet-ANFIS models can be applied as a successful tool to predict the volume of sedimentation.

Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean

“…For practical applications in hydrology, researchers have access to a discrete time signal rather than to a continuous time signal (Alizdeh et al, 2015;Rajaee et al, 2010). By using DWT, the original time series will be decomposed into various sub-signals of details (d i ) and approximations (a i ) at different resolution levels.…”

Modeling climate change impact on wind power resources using adaptive neuro-fuzzy inference system

“…In brief, an ANFIS model combines transformed data through a membership function with if-then fuzzy rules and an inference system to derive the desired results. As it gains advantages from the features of both neural networks and fuzzy logic, the ANFIS model uses the learning ability of neural networks to define the input-output relationship and construct the fuzzy rules by determining the input structure (Alizdeh, Joneyd, Motahhari, Ejlali, & Kiani, 2015). It is noted that this study does not delve into detailed descriptions of the ANFIS model, and only the technique is applied from the MATLAB ® library;…”

Modeling Climate Change Impact on Wind Power Resources Using Adaptive Neuro-Fuzzy Inference System

“…In brief, an ANFIS model is combining transformed data through membership function with ifthen fuzzy rules and an inference system to derive the desired results. Due to gaining from both features of neural networks and fuzzy logic, the ANFIS model uses the learning ability of neural networks to define the input-output relationship and construct the fuzzy rules by determining the input structure (Alizdeh, Joneyd, Motahhari, Ejlali, & Kiani, 2015). It is noted that this study is not to delve in detailed descriptions of the ANFIS model, and only the technique is applied from MATLAB library and further explanations including mathematical expressions of the method can be found in the relevant references (Alizadeh, Rajaee, & Motahari, 2016;Aqil, Kita, Yano, & Nishiyama, 2007).…”