Muhittin Aslan

Neural Network and Fuzzy Logic Implementation on Lake Ecosystems: Lake Eymir Case - Turkey Muhittin Aslan

Modeling is a helpful tool that might be used to predict the Dissolved Oxygen (DO) level of a lake. Most ecological systems are complex and unstable. In case black box models might be essential instead of deterministic ones. DO in Eymir Lake was modeled by using both Artificial Neural Networks (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS). Phosphate, Orthophospate, pH, Chlorophyll-a, Temperature, Alkalinity, Nitrate, Total Kjeldahl Nitrogen, Wind, Precipitation, Air Temperature were the input parameters of ANN and ANFIS. The aims of these modeling studies were: developing models with ANN to predict DO level in Lake Eymir with high fidelity to actual DO data, to compare the success of ANN and ANFIS on DO modeling, to determine the degree of dependence of different parameters on DO. ?Matlab R 2007b? software was used. The results indicated that ANN has high prediction capacity of DO and ANFIS has low with respect to ANN. Failure of ANFIS was due to low functionality of Matlab ANFIS. For ANN Modeling effect of meteorological data on DO data on surface of the lake was successfully described and summer month super saturation DO concentrations were successfully predicted.