SavedAdd your journal

Journals / İTÜ Dergisi Seri D: Mühendislik / 2006 / Cilt: 5 - Sayı: 3/1 3/2

Determining dissolved oxygen change using artificial neural networks: An Example of Kızılırmak River

Çözünmüş oksijen değişiminin yapay sinir ağları ile belirlenmesi: Kızılırmak Nehri örneği

Oktay ÖZKAN
Cumali KINACI
Şeref SAĞIROĞLU
Pages
30–38
Publication Date
2022-10-19
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Providing fast computation, simple structure, economic and plausible solutions determine the water qualities are the advantages of ANN encountered in this work.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, a new approach based on artificial neural networks (ANN) to determine dissolved oxygen concentration change in rivers is presented.
📊
Key Findings & Data:This parameter constitutes a significant criterion of ecological stability and activity of water.
💡
Conclusion & Impact:Providing fast computation, simple structure, economic and plausible solutions determine the water qualities are the advantages of ANN encountered in this work.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

In this study, a new approach based on artificial neural networks (ANN) to determine dissolved oxygen concentration change in rivers is presented. The dissolved oxygen concentration in rivers plays dominant role in determining the water quality. This parameter constitutes a significant criterion of ecological stability and activity of water. The ANN structures with the inputs of 27, 5, 4, and 3 have been constructed. The parameters that are most simplistic and easy to measure are used as inputs to the neural network structure to be able to observe the changes in the dissolved oxygen concentration in Kızılırmak River. The Multi Layer Perceptron (MLP) structure has been used in the phase of modeling. ANN models were trained with the extended delta-bar-delta and backpropagation learning algorithms. To achieve the task with simple configuration, 5 different data structures and two different transfer functions were tested. The best result of ANN applications is obtained with the neural network structure that uses the EDBD algorithm. The results obtained from the simulations have shown that, ANN models achieved the modeling of dissolved oxygen change with high accuracy. Providing fast computation, simple structure, economic and plausible solutions determine the water qualities are the advantages of ANN encountered in this work.

Özet

Bu çalışmada nehirlerdeki çözünmüş oksijen konsantrasyonun değişiminin modellenmesinde yapay sinir ağlarına (YSA) dayanan yeni bir yaklaşım sunulmuştur. Genişletilmiş delta-bar-delta ile geriyayılım öğrenme algoritmaları bu ağları eğitmede kullanılmıştır. Bu uygulama için en basit YSA yapısını oluşturmada 5 farklı veri yapısı ve 2 farklı transfer fonksiyonu test edilmiştir. Elde edilen sonuçlar, YSA’nın çözünmüş oksijen konsantrasyonunu belirlemede başarılı bulunmuştur. İşlemlerin hızlı hesaplanması, basit yapıda olmaları, matematiksel modellemesinin çıkarılması zor problemlere kabul edilebilir sonuçlar sunmaları, su kalite modellemesinde ekonomik çözümler sunmaları bu zeki yaklaşımın karşılaşılan üstünlükleridir.

🔖

Cite This Article

ÖZKAN, O., KINACI, C., SAĞIROĞLU, Ş. (2022). Determining dissolved oxygen change using artificial neural networks: An Example of Kızılırmak River. İTÜ Dergisi Seri D: Mühendislik, Cilt: 5 - Sayı: 3/1 3/2, 30–38. https://ajindex.com/articles/557213

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. Basheer, I.A. ve Najjar, Y.M., (1995).
  2. A Neuralnetwork for soil compaction, Proc. 5th Int. Symp. Numerical Models in Geomechanics, Davos, Switzerland (eds. Pande, G.N. & Pietruszczak, S.), Rotterdam: Balkema, 435-440.
  3. Camara, AS. ve Randall, C.W., (1984).
  4. The QUAL II Model, Journal of Environmental Engineering, 110, 993-996.
  5. Fleming, G., (1975). Computer Simulation Techniques in Hydrology, Elsevier, 319, New York. Haykin, S., (1994).
  6. Neural Networks, A Comprehensive Foundation, MacMillan College Publishing Comp. Inc., New York. Karul, C., Soyupak, S. ve Germen E., (1998). A new approach to mathematical water quality modelling reservoirs: Neural Network, International Review of Hydrobiology, 83, 689-696.
  7. Ken-ichi Y., Masaaki H. and Akihiko M., (1997). Novel application of a back-propagation artificial neural network model formulated to predict algal bloom, Water Science and Technology, 36, 89–97.
  8. Little, K.W., Williams, R.F., (1992). Least-Squares Calibration of QUAL2E, Water Research, 64, 179-185.
  9. Martin, J.L., (1988). Application of Two Dimensional Water Quality Model, Journal of Environmental Engineering, 114, 317-336. Neuralware Handbook, (1996). Neural Computing: A Technology Handbook for Professional II/PLUS and NeuralWorks Explorer, Pittsburg, USA. O’Connell, R., Thomass, N.A., (1965). Effects of Benthic Algae on Stream Dissolved Oxygen, Journal of the Sanitary Engineering, ASCE, 91, No:SA3. Rizzo, D.M. ve Dougherty, D.E., (1994). application of artificial neural networks for site characterization using hard and soft information, Proc. 10th Int. Conf. Computational Methods in Water Resources, Heidelberg (eds. Peters, A., Wittum, G., Herrling, B., Meissner, U., Brebbia, C.A., Gray, W.G. & Pinder, G.F.), Dordrecht: Kluwer Academic, 12, 793-799.
  10. Rounds, S. A., (2002). Development of a neural network model for dissolved oxygen in the Tualatin River, Oregon, In Proceedings of the Second Federal Interagency Hydroloic Modeling Conference, Las Vegas Nevada. Rumelhart, D E., McClelland, J. L., (1986). Parallel Distributed Processing: Explorations in the microstructure of Cognition, MIT Press,
  11. Cambridge, Massachusetts. Sağıroğlu, Ş., Beşdok, E. ve Erler, M., (2003). Mühendislikte yapay zeka uygulamaları I: Yapay Sinir Ağları, Ufuk Kitap Kırtasiye-Yayıncılık Tic.Ltd.Şti., Kayseri. Stamou, A.I., (1992). Improving the numerical modeling of river water quality by using high order difference schemes, Water Research, 26, 1563-1570.
  12. Streeter, H., Phelps, E., (1944).