Yazar "Ozdemir, Rahmi Can" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    An Adaptive Neuro-Fuzzy Inference System (ANFIS) to Predict of Cadmium (Cd) Concentrations in the Filyos River, Turkey
    (Central Fisheries Research Inst, 2018) Sonmez, Adem Yavuz; Kale, Semih; Ozdemir, Rahmi Can; Kadak, Ali Eslem
    Water quality is one of the main characteristics of a river system and prediction of water quality is the key factor in water resource management. Different physical, biological and chemical parameters including heavy metals can be used to assess river water quality. Evaluation of the water quality in the rivers is quite difficult and requires more time and effort because of the fact that many factors affect water quality. Traditional data processing methods are insufficient to solve this problem. Therefore, in this study, an adaptive neuro-fuzzy inference system (ANFIS) model was developed to predict the concentrations of cadmium (Cd) in the Filyos River, Turkey. For this purpose, water samples collected at 7 sampling locations in the river during December 2014-2015 were used to develop ANFIS model. The available data set was apportioned into two separate sections for training and testing the ANFIS model. Developed models aimed to use the least parameters to estimate Cd concentration. As a result, a relatively higher correlation (R-2=0.91) was found between observed and modelled Cd concentrations. The results indicated that the ANFIS model gave reasonable estimates for the concentrations of Cd with a high degree accuracy and robustness. In conclusion, this paper suggests that ANFIS methodology produce very successful findings and has the ability to predict Cd concentration in water resources. The outcomes of this research provide more information, simulation, and prediction about heavy metal concentration in natural aquatic ecosystems. Therefore, ANFIS can be used in further researches on water quality monitoring.
  • [ X ]
    Öğe
    Artificial Neural Networks Modelling for Nitrate Prediction in Surface Water of Gökırmak River (Türkiye)
    (2025) Kale, Semih; Sonmez, Adem Yavuz; Taştan, Yiğit; Kadak, Ali Eslem; Ozdemir, Rahmi Can
    This study aimed to develop an artificial neural network (ANN) model to estimate the nitrate content in the surface water of the Gökırmak River. Samplings were carried out during 12 months from six stations between 2020 and 2021. Nitrate content varied between 0.20 and 2.70 mg l-1 while the mean value was 1.18 mg l-1 during the study period. The developed model consists of two input layers (month and station) and one output layer (nitrate content). Feed-forward backprop was used as the network type. Levenberg-Marquardt (TRAINLM) was used as a training function, LEARNGDM was used as an adaption learning function and mean squared error (MSE) was used as a performance function. The number of neurons was 10 and TANSIG was selected as transfer function. Epoch number adjusted 1000 iterations. ANN model predicted the nitrate content between 0.24 and 2.61 with a mean value of 1.16 mg l-1. The results showed that the best validation performance is 0.61264 at epoch 30. R values are 0.96257 and 0.84231 for training and testing, respectively. R-value was found 0.85352 for all data. In conclusion, this study presents the conception of an artificial neural network (ANN) model designed to predict nitrate concentrations in river water. The developed ANN model provides reasonable results for predicting the nitrate content using only given time and location inputs. More inputs can be included in future studies to ensure higher accuracy in the development of ANN models.
  • [ X ]
    Öğe
    Fuzzy Logic-Based Evaluation of Physicochemical Water Quality Parameters in the Gökırmak River (Türkiye)
    (Ataturk Universitesi, 2025) Sönmez, Adem Yavuz; Kale, Semih; Taştan, Yiğit; Ozdemir, Rahmi Can; Kadak, Ali Eslem
    Traditional water quality classification methods rely on fixed threshold values, which limits their ability to reflect the degree of deviation from these boundaries. This rigid approach often results in uncertainties when assessing the ecological status of rivers. Fuzzy logic, in contrast, provides a more flexible framework by incorporating gradual transitions between classes and accounting for the relative importance of parameters. In this study, a fuzzy logic-based classification system was developed to evaluate the water quality of the Gökırmak River (Türkiye) and was compared with the conventional water quality index defined by national standards. Ten physicochemical parameters (temperature, pH, dissolved oxygen, electrical conductivity, nitrate, nitrite, ammonium, phosphate, biochemical oxygen demand, and chemical oxygen demand) were monitored monthly at six stations for one year. The fuzzy logic model was constructed using triangular membership functions and a Mamdani inference system. Model performance was assessed by comparing fuzzy classification results with expert evaluations based on the Surface Water Regulation. The system achieved 90% agreement, calculated as the ratio of consistent classifications to the total number of cases, demonstrating that fuzzy logic can serve as a reliable tool in water quality assessment. The findings highlight that fuzzy logic-based approaches not only reduce classification uncertainties but also provide a decision support framework for sustainable water resource management. Further research should expand the dataset across longer time periods and incorporate retrospective records to improve generalizability. © 2025, Ataturk Universitesi. All rights reserved.