Journal of Food, Agriculture and Environment

Predicting dissolved oxygen saturation downstream of Three Gorges dam: A support vector machine model approach 

Author(s):

Junjun Tan ^{1, 2}, Huichao Dai ^{1, 2}*, Tengfei Hu ^{1, 2}, Yu Wang ³

Recieved Date: 2013-01-07, Accepted Date: 2013-04-29

Abstract:

The dissolved oxygen supersaturation downstream of high dams can lead to gas bubble disease or even the death of fish or aquatic life, which will cause a negative effect of the water eco-environment. This paper establishes a support vector machine (SVM) model and presents eleven affecting variables representing affecting factors for predicting the dissolved oxygen saturation downstream of Three Gorges dam. The results indicate that the relative error between actual value and predicted value is less than 10%, which is much lower than the relative error of BP neural network model (considering as the control group). This implies that the SVM model can fit the actual values accurately, and highly effective in predicting dissolved oxygen saturation. The results also illustrate that the eleven affecting variables are in complex nonlinear relationships, and the affecting factors are important for predicting and controlling the supersaturation downstream of dams. The SVM model is simple and easy to apply to a practical project without any assumption and complicated parameter equations, which can be the foundation for the environmental assessment of hydropower project and the guidance for predicting and controlling the dissolved oxygen supersaturation downstream of high dams. 

Keywords:

Dissolved oxygen saturation, SVM, prediction, Three Gorges dam

---

Journal: Journal of Food, Agriculture and Environment
Year: 2013
Volume: 11
Issue: 2
Category: Environment
Pages: 977-980

---

Full text for Subscribers

---

Information:

Note to users

The requested document is freely available only to subscribers/registered users with an online subscription to the Journal of Food, Agriculture & Environment. If you have set up a personal subscription to this title please enter your user name and password. All abstracts are available for free.

Article purchasing

If you like to purchase this specific document such as article, review or this journal issue, contact us. Specify the title of the article or review, issue, number, volume and date of the publication. Software and compilation, Science & Technology, all rights reserved. Your use of this website details or service is governed by terms of use. Authors are invited to check from time to time news or information.

---

Purchase this Article:   20 Purchase PDF Order Reprints for 15

---

Share this article :