Feza Karaer

A neural network-based approach for calculating dissolved oxygen profiles in reservoirs

A Neural Network (NN) modelling approach has been shown to be successful in calculating pseudo steady state time and space dependent Dissolved Oxygen (DO) concentrations in three separate reservoirs with different characteristics using limited number of input variables. The Levenberg–Marquardt algorithm was adopted during training. Pre-processing before training and post processing after simulation steps were the treatments applied to raw data and predictions respectively. Generalisation was improved and over-fitting problems were eliminated: Early stopping method was applied for improving generalisation. The correlation coefficients between neural network estimates and field measurements were as high as 0.98 for two of the reservoirs with experiments that involve double layer neural network structure with 30 neurons within each hidden layer. A simple one layer neural network structure with 11 neurons has yielded comparable and satisfactorily high correlation coefficients for complete data set, and training, validation and test sets of the third reservoir.

Fraction distribution and risk assessment of heavy metals and trace elements in sediments of Lake Uluabat

To examine the status and risk of heavy metal pollution, the distribution of As, Cd, Cr, Ni, and Pb in the sediment of Lake Uluabat was characterized. The present study used a four-stage method to assess the ecotoxicological effects of the heavy metal and trace elements fractions in the sediment of Lake Uluabat. Total Cr and Ni concentrations in the sediment were determined to have exceeded the severe effect level (SEL) limit values. The percentages of the variable fractions of Cr and Ni were below 10%. Because of this reason, they were not defined to have a high risk. The relationships among the physicochemical parameters, heavy metals and trace elements in water and sediment were determined statistically. Pb, Cd, and As in the water were found in relation with some of the fractions. Moreover, it was thought that the amounts of the elements of As releasing into the water might be increased due to their relations with the physicochemical parameters.

Applications of Geographic Information System (GIS) analysis of Lake Uluabat

Lake Uluabat is one of the most important wetlands in Turkey because of its rich biodiversity, lying on a migratory bird route with almost all its shores being covered by submerged plants. The lake has been protected by the Ramsar Convention since 1998. However, the Lake is threatened by natural and anthropogenic stressors as a consequence of its location. Geographic Information System (GIS) analysis is a tool that has been widely used, especially for water quality management in recent years. This study aimed to investigate the water quality and determined most polluted points using GIS analysis of the lake. Temperature, pH, dissolved oxygen, chemical oxygen demand, Kjeldahl nitrogen, total phosphorus, chlorophyll-a, arsenic, boron, iron, and manganese were monitored monthly from June 2008 to May 2009, with the samples taken from 8 points in the lake. Effect of pH, relation of temperature, and Chl-a with other water quality parameters and metals are designated as statistically significant. Data were mapped using ArcGIS 9.1 software and were assessed according to the Turkish Water Pollution Control Regulations (TWPCR). The research also focused on classifying and mapping the water quality in the lake by using the spatial analysis functions of GIS. As a result, it was determined that Lake Uluabat belonged to the 4th class, i.e., highly polluted water, including any water of lower quality. A remarkable portion of the pollution in the water basin was attributed to domestic wastewater discharges, industrial and agricultural activities, and mining.

Adaptive neuro-fuzzy inference technique for estimation of light penetration in reservoirs

An adaptive neuro-fuzzy inference technique has been adopted to estimate light levels in a reservoir. The data were collected randomly from Doğanci Dam Reservoir over a number of years. The input data set is a matrix with vectors of time, depth, sampling location, and incident solar radiation. The output data set is a vector representing light measured at various depths. Randomization and logarithmic transformations have been applied as preprocessing. One-half of the data have been utilized for training; testing and validation steps utilized one-fourth each. An adaptive neuro-fuzzy inference system (ANFIS) has been built as a prediction model for light penetration. Very high correlation values between predictions and real values on light measurements with relatively low root mean square error values have been obtained for training, test, and validation data sets. Elimination of the overtraining problem was ensured by satisfying close root mean square error values for all sets.

The role of different kinds of particles on heavy metals in Lake Uluabat sediments

ABSTRACT The concentrations of Cu, Zn, Pb, Cr, Fe, Mn, and Ni and other sediment quality parameters (percentage of organic matter, calcium carbonate, total carbon, total nitrogen, and total phosphorus) were investigated seasonally in Lake Uluabat (Turkey) sediments (May 2008–May 2009) to reveal the sources of biological material and to determine the effect of the settling particle compositions on heavy metal transport. Examination of seasonal variations and correlation coefficients calculated among the parameters showed that settling biological material was an important carrier phase, especially for Cr, Cu, Pb, Fe, and Mn. The metals and nutrients in the lake could come from the same pollution sources. According to the C:N:P ratios of the sediments, it was discovered that biologic materials originated from algae population and domestic and industrial wastewaters. Iron and manganese cycling was also a contributor to trace element transport, while calcium carbonate formations were determined to be inefficient carrier material.