An Integrated Evaluative Function and Water Bloom Predicting and Prewarning System

Abstract:

An integrated evaluative function and prediction model and prewarning system for water bloom in lakes based on Elman neural network is proposed in this paper, in which main influence factor of outbreak of water bloom is analyzed by rough set theory. The study of the function involves some aspects: algal average activation energy of photosynthesis, integrated nutritional status index, and transparency, which are considered from the microcosmic level, the macroscopic level and the intuitionistic level respectively. The values of the function are classified properly. Combined with the basic features of outbreak of water-bloom, Elman network is studied from the angles of theory and experiment and a water-bloom prewarning system in short term based on Elman network is established. The results of simulation and application show that: Elman neural network improves the algorithm of BP neural network, it has long-term prediction period, strong generalization ability， high prediction accuracy; and needs a small amount of sample and this model provides an efficient new way for short-term water bloom prediction, And approaching ability of Elman network is more superficial than common static networks and its velocity of convergence is faster.

• Periodical: Advanced Materials Research (Volumes 476-478)
• Pages: 2427-2434
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.476-478.2427
• Online since: February 2012
• Authors: Zai Wen Liu, Xiao Yi Wang, Qiao Mei Wu
• Keywords: Elman Neural Network (ENN), Evaluation Method, Integrated Nutritional Index, Prewarning System, Water Bloom Prediction

References

[1] Xiangcan Jin, Zhaochun Li, Sufang Zheng: Growth characteristics of microcystis aeruginosa. Environmental Science Research(2004).

[2] Huo W Y, Hao J H, Yu Z M: A review of harmful red tide numerical analysis. Oceanologia et Limnologia Sinica ,1999,30(50：568-574.

[3] Wu H J, Lin Z Y and Guo S L.:Application of artificial neural network in predicting resources and environment. Resource and Environment in the Yangtze Basin, 2000,9(2):237-241.

[4] Simeonov V, Stefanov S, Tsakovski S.: Environmental Treatment of Water Quality Survey Data from Yangtse River. Mikrochim Acta. 2000, 134 (122): 15-21.

DOI: 10.1007/s006040070047

[5] Wan Z W, Yuan Y L and Qiao F.: Study on optimization of the parameters of marine ecosystem dynamic model for red tide. Oceanologia et Limnologia Sinica .2000,31(2):205-209.

[6] Zhou M Ｌ, Zhu M Y and Zhang J. :Trends of harmful algal blooms and related research advances in China. Chinese Bulletin of Life Science. 2001,13(2):54-60.

[7] Zeng G M, Lu H W: Assessment of the Water Quality and Nutrition of the Dongting Lake with Wavelet Neural Network. Journal of Hunan University. 2005，32(1):91—94.

[8] Lou W G.: Eutrophication assessment model using artificial neural networks for lakes and reservoirs. Journal of Fisheries of China.2001，25(5):474-478.

[9] Zaiwen Liu, Qiaomei Wu, Xiayi Wang, Lifeng Cui, XiaoFeng Lian. Algal growth based on the optimization theory model and the application of the water bloom prediction [J]. Chemical Journal, 2008, 59(7):1869-1873

DOI: 10.1109/wcica.2008.4594413