WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7150
Browse
7 results
Search Results
Now showing 1 - 7 of 7
Article Citation - WoS: 27Citation - Scopus: 29Fuzzy, Ann, and Regression Models To Predict Longitudinal Dispersion Coefficient in Natural Streams(IWA Publishing, 2006) Tayfur, GökmenThis study developed fuzzy, ANN, and regression-based models to predict longitudinal dispersion coefficient in natural streams from flow discharge data. 92 sets of field data were employed to calibrate and validate the models. 63 sets of data were used for the calibration while the remaining data were used for the validation of the models. The model-prediction results revealed the superiority of the developed models over the existing equations. The developed models predicted the measured data satisfactorily with minimum errors and maximum accuracy rates. The three models had comparable performances although the fuzzy model had the highest accuracy rate (79%) and lowest mean relative error (0.85).Article Citation - WoS: 44Citation - Scopus: 47Predicting Flood Plain Inundation for Natural Channels Having No Upstream Gauged Stations(IWA Publishing, 2019) Kaya, C. Melisa; Tayfur, Gökmen; Güngör, OğuzFlow hydrographs are one of the most important key elements for flood modelling. They are recorded as time series; however, they are not available in most developing countries due to lack of gauged stations. This study presents a flood modelling method for rivers having no upstream gauged stations. The modelling procedure involves three steps: (1) predicting upstream hydrograph by the reverse flood routing method which requires information about channel geometric characteristics, downstream flow stage and downstream flow hydrographs; (2) modelling flood wave spreading using HEC-RAS. The hydrograph predicted by the reverse flood routing in the first step becomes an inflow for the HEC-RAS model; (3) delineating the flood-risk areas by overlapping the Geographical Information System (GIS)-based flood maps produced by the HEC-RAS to the related orthophoto images. The developed model is applied to Guneysu Basin in Rize Province in Eastern Black Sea Region of Turkey. The model-produced flood map is compared to the observed one with success.Article Citation - WoS: 33Citation - Scopus: 37Trend Analysis of Temperature and Precipitation in Trarza Region of Mauritania(IWA Publishing, 2019) Yacoub, Ely; Tayfur, GökmenTrend analysis of annual temperature and precipitation time series data collected from three stations (Boutilimit (station 1), Nouakchott (station 2) and Rosso (station 3)) has been used to detect the impacts of climate change on water resources in Trarza region, Mauritania. The Mann-Kendall, the Spearman's rho, and the Sen trend test were used for the trend identification. Pettitt's test was used to detect the change point of the series while the Theil-Sen approach was used to estimate the magnitude of the slope in the series. For precipitation, two stations (1 and 3) indicated statistically significant increase in trends. In the case of temperature, almost all the stations show statistically significant increasing trends in the maximum, minimum, and average temperatures. The magnitude of precipitation detected by the Theil-Sen test for stations 1 and 3, respectively, was found to be at the rate of 2.93 and 3.35 mm/year at 5% significance level. The magnitude trend of temperature detected by the Theil-Sen approach was found to be at the rate of 0.2-0.4 degrees C per decade for almost all the stations. The change points of temperature trends detected by Pettitt test are found to be in the same year (1995) for all the stations.Article Citation - WoS: 72Citation - Scopus: 79Artificial Neural Networks for Estimating Daily Total Suspended Sediment in Natural Streams(IWA Publishing, 2006) Tayfur, Gökmen; Güldal, VeyselEstimates of sediment loads in natural streams are required for a wide spectrum of water resources engineering problems from optimal reservoir design to water quality in lakes. Suspended sediment constitutes 75-95% of the total load. The nonlinear problem of suspended sediment estimation requires a nonlinear model. An artificial neural network (ANN) model has been developed to predict daily total suspended sediment (TSS) in rivers. The model is constructed as a three-layer feedforward network using the back-propagation algorithm as a training tool. The model predicts TSS rates using precipitation (P) data as input. For network training and testing 240 sets of data sets were used. The model successfully predicted daily TSS loads using the present and past 4 days precipitation data in the input vector with R2 = 0.91 and MAE = 34.22 mg/L. The performance of the model was also tested against the most recently developed non-linear black box model based upon two-dimensional unit sediment graph theory (2D-USGT). The comparison of results revealed that the ANN has a significantly better performance than the 2D-USGT. Investigation results revealed that the ANN model requires a period of more than 75 d of measured P-TSS data for training the model for satisfactory TSS estimation. The statistical parameter range (xmin - xmax) plays a major role for optimal partitioning of data into training and testing sets. Both sets should have comparable values for the range parameter.Article Citation - WoS: 1Citation - Scopus: 1Finite Volume Method Solution of Pollutant Transport in Catchment Sheet Flow(IWA Publishing, 2014) Tayfur, Gökmen; He, Zhiguo; Ran, QihuaA finite volume numerical method was employed in the solution of two-dimensional pollutant transport in catchment sheet flow. The full dynamic wave constituted the sheet flow while the advection-diffusion equation with sink/source terms was the pollutant transport model. It is assumed that the solute in the surface active layer is uniformly distributed and the exchange rate of the solute between the active layer and overland flow are proportional to the difference between the concentrations in soil and water volume. Decrease of the solute transfer rate in the active surface layer caused by the transfer of solutes from soil to the overlying runoff is assumed to follow an exponential law. The equations governing sheet flow and pollutant transport are discretized using the finite volume method in space and an implicit backward difference scheme in time. The model was subjected to several numerical tests involving varying microtopographic surface, roughness, and infiltration. The results revealed that spatially varying microtopography plays an important role unlike the roughness and infiltration with respect to the total pollutant rate from the outlet of a catchment.Article Citation - WoS: 4Citation - Scopus: 5Use of Principal Component Analysis in Conjunction With Soft Computing Methods for Investigating Total Sediment Load Transferability From Laboratory To Field Scale(IWA Publishing, 2014) Tayfur, Gökmen; Karimi, YasharThis study quantitatively investigates the generalization from laboratory scale to field scale using the soft computing (expert) and the empirical methods. Principal component analysis is utilized to form the input vector for the expert methods. Five main dimensionless parameters are used in the input vector of artificial neural networks (ANN), calibrated with laboratory data, to predict field total sediment loads. In addition, nonlinear equations are constructed based upon the same dimensionless parameters. The optimal values of the exponents and constants of the equations are obtained by the genetic algorithm (GA) method using the laboratory data. The performance of the sodeveloped ANN and GA based models are compared against the field data and those of the existing empirical methods, namely Bagnold, Ackers and White, and Van Rijn. The results show that ANN outperforms the empirical methods. The results also show that the expert models, calibrated with laboratory data, are capable of predicting field total loads and thus proving their transferability capability. The transferability is also investigated by a newly proposed equation which is based on the Bagnold approach. The optimal values of the coefficients of this equation are obtained by the GA. The performance of the proposed equation is found to be very efficient.Article Citation - WoS: 24Citation - Scopus: 24GA-optimized model predicts dispersion coefficient in natural channels(IWA Publishing, 2009) Tayfur, GökmenModels whose parameters were optimized by genetic algorithm (GA) were developed to predict the longitudinal dispersion coefficient in natural channels. Following the existing equations in the literature, ten different linear and nonlinear models were first constructed. The models relate the dispersion coefficient to flow and channel characteristics. The GA model was then employed to find the optimal values of the constructed model parameters by minimizing the mean absolute error function (objective function). The GA model utilized an 80% cross-over rate and 4% mutation rate. It started each computation with a population of 100 chromosomes in the gene pool. For each model, while minimizing the objective function, the values of the model parameters were constrained between [-10, +10] at each iteration. The optimal values of the model parameters were obtained using a calibration set of 54 out of 80 sets of measured data. The minimum error was obtained for the case where the model was a linear equation relating dispersion coefficient to flow discharge. The model performance was then satisfactorily tested against the remaining 26 measured validation datasets. It performed better than the existing equations. it yielded minimum errors of MAE = 21.4m2/s (mean absolute error) and RMSE = 28.5m2/s (root mean-squares error) and a maximum accuracy rate of 81%. © IWA Publishing 2009.