Sabahattin Isik

Deriving Spatially Distributed Precipitation Data Using the Artificial Neural Network and Multilinear Regression Models

Precipitation is the primary driver for hydrologic modeling. Because hydrologic models often require long-term, spatially dis- tributed precipitation data sets for calibration and validation, a novel approach was developed to generate spatially distributed precipitation data using an artificial neural network (ANN) for the periods when Next-Generation Weather Radar (NEXRAD) data are either unavailable or the quality of the NEXRAD data is not good. The multilinear regression (MLR) technique was also evaluated for completeness. The studys focus was the Saugahatchee Creek watershed in southeast Alabama. In the study area, thewet seasons are dominated by frontal precipitations, whereas the dry seasons primarily contain patchy, convective thunderstorms. The basic approach was to train and validate the ANN and MLR models using recent NEXRAD and rain gauge precipitations, and then use the trained model with the rain gauge precipitation data to generate past, spatially distributed precipitation estimates at the NEXRAD grid locations. For the testing period, the ANN-simulated wet season precipitations in all the NEXRAD grids had a Nash-Sutcliffe efficiency greater than or equal to 0.72 and a mass balance error less than or equal to 14%. The same model performance parameters were 0.65 and 17%, respectively, for the dry season. The MLR model did not perform as well as the ANN model. For the MLR model, the wet season mass balance error ranged from 13-48%, whereas the dry season mass balance error ranged from 0.1-36% on the testing data set. An uncalibrated soil and water assessment tool model was used to assess the improvements in stream flow simulations with the ANN-simulated spatially distributed precipitation data. The stream flow simulations using ANN-generated, spatially distributed precipitations were closer to the observed stream flows relative to stream flows generated using the rain gauge precipitations. Overall, the results suggest that the method developed in this study can be used to generate past, spatially distributed precipitations at NEXRAD grid locations. DOI: 10.1061/(ASCE)HE.1943-5584.0000617.

Nutrient Dynamics in Flooded Wetlands. I: Model Development

AbstractWetlands are rich ecosystems recognized for ameliorating floods, improving water quality, and providing other ecosystem benefits. This part of a two-paper series presents a relatively detailed process-based model for nitrogen and phosphorus retention, cycling, and removal in flooded wetlands. The model captures salient features of nutrient dynamics and accounts for complex interactions among various physical, biogeochemical, and physiological processes. The model simulates oxygen dynamics and the impact of oxidizing and reducing conditions on nitrogen transformation and removal, and approximates phosphorus precipitation and releases into soluble forms under aerobic and anaerobic conditions, respectively. Nitrogen loss pathways of volatilization and denitrification are explicitly accounted for on a physical basis. Processes in surface water and the bottom-active soil layer are described by a system of coupled ordinary differential equations. A finite-difference numerical scheme is implemented to so...

Prediction of water quality parameters using an Artificial Neural Networks model.

Land use and cover (LULC) play crucial roles in driving water quantity and quality processes in watersheds. Often changes in LULC have direct effect on water quality of downstream waters. Therefore, developing relationships between LULC and water quality parameters is essential for the evaluation of surface water resources should the LULC change. In this paper we present a methodology based on Artificial Neural Networks (ANN) to predict water quality parameters in ungauged basins; Chlorine (Cl), Sulfate (SO4), Sodium (Na), Potassium (K), Dissolved Organic Carbon (DOC). The model relies on LULC percentages, temperature, and flow discharge as inputs. The approach is tested on 18 watersheds in west Georgia varying in size from 296 to 2659 ha. Total number of data for each parameter is 801 ranging from 15 to 54 from 18 watersheds. Out of 18 watersheds, 12 were selected for training, 3 for validation and 3 for testing the ANNs model. Each set of validation and testing data consists of 1 forested, 1 pastoral, and 1 urban watershed while training data consist of 7 forested, 3 pastoral, and 2 urban watersheds. The model performance was measured with coefficient of determination (R 2 ), Nash- Sutcliffe efficiency coefficient (E), and bias ratio (RB). The model developed using the training data set has successfully predicted the water quality parameters in the independent testing watersheds. The coefficient of determination (R 2 ) in the test watersheds ranged from 0.64 to 0.99 while E ranged from 0.54 to 0.98. Results from this study indicates that if water quality and LULC data are available from multiple watersheds in an area with relatively similar physiographic properties, then one can successfully predict the impact of LULC changes on water quality in any watershed within the same area.

Classification of River Yields in Turkey with Cluster Analysis

Clustering is necessary for lack of data in a basin based on hydrometeorological homogeneity. Even principal characteristics of river basins, such as; climate, geology, and topography affecting water yields are different, some of them yield similar hydrologic outcome. In this study, 1410 stations of Turkey Rivers were classified by the cluster analysis on the basis of hydrological homogeneity. Monthly average yields (m 3 /s/km 2 ) of 1410 river gauge stations on 26 river watersheds were used. It is aimed that the clusters to be homogeneous, the elements of the same cluster to be similar while they are not similar to those of a different cluster and the most meaningful groups to be made. The cluster number was found by using the agglomerative hierarchical cluster analysis method. Tests were conducted that stations from different geographic locations are considered in the same cluster independent of their geographic position. Turkey river basins were separated into 6 homogeneous regions and the yield distribution map of Turkey was obtained.

Optimal Dynamic Water Allocation for Irrigation of Multiple Crops

A dynamic irrigation scheduling method was developed for optimal water allocation from an irrigation reservoir and maximum net benefit from multiple crops under wet, average, and drought conditions. The model integrates two control volumes: (i) the plant root zone, which demands water, and (ii) the reservoir, which supplies water. The FAO Penman-Monteith Method was used to compute the reference crop evapotranspiration (ET0). Optimal allocation of water supply in the reservoir was determined by a dynamic programing method. The model allows for variable decision intervals for each crop. Since soil moisture exhibits a dynamic structure, various scenarios were developed for probable soil moisture deficit ratios. The objective function of the model developed in this study consists of the yield sensitive factor (Ky), the actual evapotranspiration (ETa), the potential evapotranspiration (ETm), the maximum crop yield (Ym), the benefit of unit yield in unit area (UB), the unit cost of unit yield in unit area (UC), is the unit cost of water of unit yield in unit area (UCW), and the crop area (AREA). The applicability of the method was demonstrated through a case study of Cavdarhisar Dam irrigation field (5000 ha) in Kutahya, Turkey. From the commonly grown crops in the area, wheat, maize, sunflower, potato, onion, sugar beet, beans, tomato, chickpea, and melonwatermelon were selected to be planted. Optimum water allocation scheduling of available water in the reservoir was determined based on maximum net benefit from multiple crops under wet average, and drought conditions.