Ersin Kivrak

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.

Predicting dominant phytoplankton quantities in a reservoir by using neural networks

The Levenberg–Marquardt algorithm was used to train artificial neural networks to predict the abundance of Cyclotella ocellata Pant. and Cyclotella kützingiana Thwaites using time, depth, temperature, pH, dissolved oxygen, and electrical conductivity as input parameters for the oligo-mesotrophic Kuzgun Dam Reservoir, Turkey. The data were collected in monthly intervals during two ice-free seasons: between April 2000–November 2000 and April 2001–November 2001. To reduce over-fitting of the neural network based models, we employed single hidden layer networks with early stopping of training. Correlation coefficients of neural network predictions with measurements of abundance of Cyclotella ocellata Pant. and Cyclotella kützingiana Thwaites were 0.88 and 0. 86, respectively.

Seasonal and long term changes of the phytoplankton in the lake Tortum in relation to environmental factors, Erzurum, Turkey

Seasonal changes in phytoplankton community structure of the lake Tortum were studied over one year period, from March 2002 to February 2003. The collected data were compared with the data collected 21 years ago. Chlamydomonas microsphaerella, Cyclotella krammeri, C. glomerata, and Ceratium hirundinella were identified to be dominant several times during the study period. Species diversity and biomass of the phytoplankton were very low in spite of sufficient and high levels of nutrient concentrations. Maximum phytoplankton density levels were observed during summer and late autumn. Phytoplankton density was positively correlated with nutrients, temperature and pH, and it was negatively correlated with Secchi depth and dissolved oxygen. Phytoplankton growths were negatively affected from water transparency and high levels of water mass transport (circulation) and velocity in the lake.

Seasonal Changes in Phytoplankton Community Structure in a High Mountain Reservoir, Kuzgun Reservoir, Turkey

ABSTRACT Seasonal changes in phytoplankton community structure of Kuzgun reservoir, a high mountain reservoir, were studied during the ice-free period in 2000 and 2001. Bacillariophyta was the dominant group, followed by Chlorophyta and Dinophyta. The dominant species were Synedra delicatissima, Asterionella formosa, Fragilaria crotonensis, Cyclotella kützingiana, Cyclotella ocellata, Oocystis borgei, Staurastrum longiradiatum, Ankistrodesmus falcatus, Ceratium hirundinella, and Peridinium cinctum. Maximum phytoplankton density was observed in late spring.