Gene Expression Programing for Estimating Suspended Sediment Yield in Middle Euphrates Basin, Turkey

Abstract

Gene expression programing (GEP) is used to estimate the suspended sediment yield (SSY) in Euphrates River. SSY is considered to be a function of (i) discharge and (ii) timelagged discharge and SSY. The proposed models were trained to extrapolate natural stream data collected from five stations in Middle Euphrates Basin. A detailed sensitivity analysis is done to select the time-lagged discharge and sediment yield variables. GEP implicitly evaluates the contribution of each independent variable on the fitness of candidate solution and eliminates the variable having no contribution. In this study, all input variables are observed to be included in the proposed GEP models, which prove the significance of each variable. Also, standard and modified sediment rating curves and regression-based formulae are developed for the five stations. In verification, the estimations of GEP formulae agree well with the measured ones. The GEP models are evaluated by the results of the rating curves and regression formulae. In general, the GEP formulae give better results compared to the rating curves and regression-based formulae.

Streamflow Forecasting and Estimation Using Least Square Support Vector Regression and Adaptive Neuro-Fuzzy Embedded Fuzzy c-means Clustering

“…In the last decades, the application of artificial intelligence has received much attention in water resources (Kisi 2006(Kisi , 2007Guven 2009;Guven and Talu 2010;Kumar et al 2011;Mustafa et al 2012;Sanikhani and Kisi 2012;Awchi 2014). Recently, the support vector regression (SVR) has been widely used in solving hydrologic problems (Sivapragasam et al 2001;Vapnik et al 1997;McNamara et al 2005;Awad et al 2007;Kaheil et al 2008;Kisi and Cimen 2009;Chen et al 2010;He et al 2014).…”

Semi-theoretical approach to optimisation of gate ratio for small concrete dams and weirs

“…The genetic algorithm has been applied in the optimisation of the design of gravity dams (Salmasi, 2011), optimisation of dam construction cost (Silvoso, Faibairn, Filho, Edbecken, & Alves, 2003) and optimal design of fuse gates considering water loss due to gates tilting (Afshar & Takbiri, 2009). Successful applications of GP, recorded in water resources engineering (Giustolisi, 2004;Guven, Aytek, Yuce, & Aksoy, 2008;Guven & Gunal, 2008;Rabuñal, Puertas, Suárez, & Rivero, 2007), have drawn the hydrologists in investigating the use of GP in estimating the river flow data (Guven, 2009;Guven & Talu, 2010). Linear Genetic Programming (LGP) is a particular subset of GP wherein computer programs in population are represented as a sequence of instructions from imperative programming language or machine language.…”

Bayesian Regression and Neuro-Fuzzy Methods Reliability Assessment for Estimating Streamflow

“…However, these methods fall short of capturing hydrological responses to significant changes in physiographical (e.g., land-use/land-cover) and climatological (e.g., climate change) characteristics of a watershed. Artificial neuro-fuzzy inference systems (ANFIS) and Bayesian regression methods have received more attention in recent years in the water resources field due to their ability to model sophisticated non-linear systems such as streamflow and contaminant transport [25][26][27][28][29][30][31][32][33].…”