Yüzeysel sularda benzen mikrokirleticisinin tespiti ve modellenmesi: Orhaneli çayı örneği
Yükleniyor...
Tarih
2020
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Aksaray Üniversitesi Fen Bilimleri Enstitüsü
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Öncelikli mikrokirleticiler, günümüzde gittikçe artan konsantrasyonları ve su ortamlarındaki dirençli yapıları sebebiyle önemli bir araştırma konusudur. Özellikle, madencilik faaliyetleri, termik santrallerin yaygınlaşması, motorlu taşıtların kullanımının artması ve sanayinin gelişmesi ile öncelikli mikrokirletici varlığına neden olan kaynaklar gün geçtikçe artmaktadır. Bu çalışmada sanayi ve madencilik faaliyetlerinin yoğun olarak yapıldığı, termik santrallerin bulunduğu bir bölgede bulunan Orhaneli Çayı'nda öncelikli mikrokirleticilerden olan benzen kirleticisinin 12 ay boyunca izlemesi yapılmıştır. Modelleme çalışmasında yapay sinir ağları kullanılarak benzen mikrokirleticisinin tahmin modeli yapılmış olup; meteorolojik, bazı fiziksel ve kimyasal parametrelerin benzen konsantrasyonları üzerine olan etkileri incelenmiştir. Yapay sinir ağları yapısı, bir girdi katmanı, bir gizli katman ve bir de çıktı katmanından oluşmaktadır. Temel bileşen analizi uygulamasından sonra yapay sinir ağları girdi parametreleri olarak yağış, sıcaklık, nem, pH, debi, çözünmüş oksijen, iletkenlik, toplam organik karbon ve toplam azot kullanılmıştır. Ağ oluşturulurken 11 farklı geri yayılım algoritması kendi içerisinde ortalama karesel hata değerleri ile karşılaştırılmış ve Levenberg – Marquardt algoritması en iyi eğitim algoritması olarak belirlenmiştir. Seçilen eğitim algoritması için üretilen benzen konsantrasyonu tahmininde gizli katmanda kullanılacak optimize nöron sayısı 6 olarak bulunmuştur. Optimize edilen üç katmanlı yapay sinir ağları modeli (9:6:1) için korelasyon katsayısı (R2) 0.9889 olarak elde edilmiştir. Yapılan çalışma sonucunda açıkça görülmektedir ki, yapay sinir ağları tabanlı model sonuçlarının yüzeysel sulardaki benzen konsantrasyonu için kullanımı oldukça uygundur.
Priority micro-pollutants are an important research topic today due to their increasing concentration and their resistant structure in water environments. Particularly, mining activities, the widespread of thermal power plants, the increase in the use of motor vehicles and the development of the industry, the resources that cause the priority micro-pollutant existence are increasing day by day. In this study, benzene pollutant, which is one of the primary micro-pollutants, was monitored for 12 months. Orhaneli river, which is located in an area where industrial and mining activities are carried out intensely and where thermal power plants are located, has been chosen as the study area. In the modeling study, an estimation model of the benzene pollutant was made using artificial neural networks; the effects of meteorological, some physical and chemical parameters on benzene concentrations were investigated. Artificial neural networks structure consists of an input layer, a hidden layer and an output layer. After basic component analysis application, artificial neural networks are used as input parameters, precipitation, temperature, humidity, pH, flow rate, dissolved oxygen, conductivity, total organic carbon and total nitrogen. While creating the network, 11 different back propagation algorithms were compared with mean square error values and Levenberg - Marquardt algorithm was determined as the best training algorithm. In the estimation of benzene concentration produced for the selected training algorithm, the number of optimized neurons to be used in the hidden layer was found to be 6. The correlation coefficient (R2) for the optimized three-layer artificial neural network model (9:6:1) was obtained as 0.9889. As a result of the study, it can be clearly seen that the results of artificial neural network based models are quite suitable for the concentration of benzene in surface waters.
Priority micro-pollutants are an important research topic today due to their increasing concentration and their resistant structure in water environments. Particularly, mining activities, the widespread of thermal power plants, the increase in the use of motor vehicles and the development of the industry, the resources that cause the priority micro-pollutant existence are increasing day by day. In this study, benzene pollutant, which is one of the primary micro-pollutants, was monitored for 12 months. Orhaneli river, which is located in an area where industrial and mining activities are carried out intensely and where thermal power plants are located, has been chosen as the study area. In the modeling study, an estimation model of the benzene pollutant was made using artificial neural networks; the effects of meteorological, some physical and chemical parameters on benzene concentrations were investigated. Artificial neural networks structure consists of an input layer, a hidden layer and an output layer. After basic component analysis application, artificial neural networks are used as input parameters, precipitation, temperature, humidity, pH, flow rate, dissolved oxygen, conductivity, total organic carbon and total nitrogen. While creating the network, 11 different back propagation algorithms were compared with mean square error values and Levenberg - Marquardt algorithm was determined as the best training algorithm. In the estimation of benzene concentration produced for the selected training algorithm, the number of optimized neurons to be used in the hidden layer was found to be 6. The correlation coefficient (R2) for the optimized three-layer artificial neural network model (9:6:1) was obtained as 0.9889. As a result of the study, it can be clearly seen that the results of artificial neural network based models are quite suitable for the concentration of benzene in surface waters.
Açıklama
Anahtar Kelimeler
Orhaneli Çayı, Yüzeysel Sularda Benzen Mikrokirleticisinin Tespiti, Determination and Modeling of Benzene Micropollutant
