Good data analysis is required for the optimal design of water resources projects. However, data are not regularly collected due to material or technical reasons, which results in incomplete-data problems. Available data and data length are of great importance to solve those problems. Various studies have been conducted on missing data treatment. This study used data from the flow observation stations on Yeşilırmak River in Turkey. In the first part of the study, models were generated and compared in order to complete missing data using Artificial Neural Network Fuzzy Inference Systems (ANFIS), multiple regression and Normal Ratio Method. Thus, it is tried to define the usability besides the other model to complete the missing data. Likewise, in the study. It is aimed to define the minimum number of data necessary for the use age of ANFIS. For this purpose in the second part of the study, the minimum number of data required for ANFIS models was determined using the optimum ANFIS model. Of all methods compared in this study, ANFIS models yielded the most accurate results. A 10-year training set was also found to be sufficient as a data set.

Good data analysis is required for the optimal design of water resources projects. 10However, data are not regularly collected due to material or technical reasons, which results in 11 incomplete-data problems. Available data and data length are of great importance to solve those 12 problems. Various studies have been conducted on missing data treatment. This study used data 13 from the flow observation stations on Yeşilırmak River in Turkey. In the first part of the study, 14 models were generated and compared in order to complete missing data using ANFIS, multiple 15 regression and Normal Ratio Method. In the second part of the study, the minimum number of data 16 required for ANFIS models was determined using the optimum ANFIS model. Of all methods 17 compared in this study, ANFIS models yielded the most accurate results. A 10-year training set was 18 also found to be sufficient as a data set. 19

Giderek azalan su kaynaklarının etkili biçimde kullanılması ve gelecek için su kaynaklarının doğru planlanması önemlidir. Su kaynaklarının planlanması çalışmalarında akım modellemeleri ve akım tahminleri yapmak çalışmaların temelini oluşturmaktadır. Bu çalışmada Sandıklı Kestel barajına ait 1986-2008 yılı verileri ile ANFIS modeli kullanılarak aylık hacimlerin tahmini yapılmaya çalışılmıştır. Sistemde girdi olarak önceki aylara ait hacimler, hazneye giren ve çıkan hacimler ve buharlaşma miktarı kullanılmıştır. ANFIS yönteminde girdiler için kullanılan küme sayıları ise K-ortalamalar yöntemi ile elde edilmiştir. K-ortalamalar yönteminden elde edilen küme sayıları ile oluşturulan farklı kümeler ANFIS'te modellenmiş ve sonuçlar karşılaştırılmıştır. Her bir girdi değeri için en uygun küme sayıları belirlenmiş ve bu doğrultuda modelleme yapılmıştır. Sonuç olarak uygun küme sayılarına göre yapılan modellerin rastgele oluşturulan modellere göre daha düşük hata yüzdesine sahip sonuçlar verdiği belirlenmiştir.Correct planning of water resources is important for the efficient use of rapidly decreasing water resources in the future. Flow modeling and flow estimations in the planning of water resource are the basis of studies. In this study, it is aimed to estimate monthly volumes by using ANFIS model based on the data of 1986-2008 for Sandıklı Kestel dam. In the system, the volume of the previous months, the volume of the incoming and outgoing volumes and the amount of evaporation were used as input variables. In ANFIS method, the number of clusters used for the inputs was obtained by the method of K-means. Different clusters formed by K-averages were modeled in ANFIS and the results were compared. The optimal number of clusters for each input value is determined. Models have been established in this way. As a result, it has been found that the models made according to the optimal number of clusters yield results with lower error percentage compared to randomly generated models.

No abstract

Water is essential for living organisms. The increase in world population, global climate change and rapid growth in industrialization and urbanization have brought with them water issues around the world in recent years. Not only should existing water resources be used reasonably and efficiently but alternative water resources should also be explored and secured. Rainwater harvesting, which is one of the alternative water resources, can provide economic and environmental solutions. For rainwater harvesting, the size of reservoirs in which rainwater captured from roof catchments is stored should be determined. Determining the optimum tank capacity depending on precipitation and consumption rates allows us to make maximum use of rainwater tanks. The aim of this study is to determine the optimum tank capacity for the storage of rainwater captured from roof catchments in order to meet the water demand for agricultural production. Precipitation data were collected from the city of Isparta and its districts. Rainwater tank capacity was determined using the Rippl, residual mass curve, minimum flow and particle swarm optimization methods. Storage capacities varying according to roof areas and consumption rates are shown in a graph. Results show that particle swarm optimization is the best method.