Elman's Recurrent Neural Network Applied to Forecasting Algal Dynamic Variation in Gonghu Bay

Abstract:

This paper describes the training, validation and application of recurrent neural network (RNN) models to computing the algal dynamic variation at three sites in Gonghu Bay of Lake Taihu in summer. The input variables of Elmans RNN were selected by means of the canonical correspondence analysis (CCA) and Chl_a concentration as output variable. Sequentially, the conceptual models for Elmans RNN were established and the Elman models were trained and validated on daily data set. The values of Chl_a concentration computed by the models were closely related to their respective values measured at the three sites. The correlation coefficient (R²) between the predicted Chl_a concentration by the model and the observed value were 0.86-0.92. And sensitivity analysis was performed to clarify the algal dynamic variation to the change of environmental factors. The results show that the CCA can efficiently ascertain appropriate input variables for Elmans RNN, the Elmans RNN can precisely forecast the Chl_a concentration at three different sites in Gonghu Bay of Lake Taihu in summer and sensitivity analysis validated the algal dynamic variation to the change of environmental factors which were selected by CCA.

• Periodical: Advanced Materials Research (Volumes 779-780)
• Pages: 1352-1358
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.779-780.1352
• Online since: September 2013
• Authors: He Yi Wang, Xu Chang Yang
• Keywords: Algal Dynamic Variation, Canonical Correspondence Analysis (CCA), Elmans Recurrent Neural Network

References

[1] Asaeda, T., Bon, T.V., 1997. Modelling the effects of macrophytes on algal blooming in eutrophic shallow lakes. Ecol. Model. 104, 261-287.

DOI: 10.1016/s0304-3800(97)00129-4

[2] Webster, I.T., Sherman, B.S., Bormans, M., Jones, G., 2000. Management strategies for cyanobacterial blooms in an impounded lowland river. Regul. Rivers: Res. Manage. 16, 513-525.

DOI: 10.1002/1099-1646(200009/10)16:5<513::aid-rrr601>3.0.co;2-b

[3] Maier, H.R., Burch, M.D., Bormans, M., 2001. Flow management strategies to control blooms of the cyanobacterium, Anabaena circinalis, in the River Murray at Morgan South Australia. Regul. Rivers: Res. Manage. 17, 637-650.

DOI: 10.1002/rrr.623

[4] Jeong, K. -S., Kim, D. -K., Whigham, P., Joo, G. -J., 2003a. Modelling Microcystis aeruginosa bloom dynamics in the Nakdong River by means of evolutionary computation and statistical approach. Ecol. Model. 161, 67-78.

DOI: 10.1016/s0304-3800(02)00280-6

[5] Recknagel, F., 1997. ANNA-Artificial Neural Network model for predicting species abundance and succession of blue-green algae. Hydrobiologia 349, 47-57.

[6] Maier, H.R., Dandy, G.C., 2001. Neural Network Based Modelling of Environmental Variables: A Systematic Approach. Mathematical and Computer Modeling 33, 669-682.

DOI: 10.1016/s0895-7177(00)00271-5

[7] Wei, B., Sugiura, N., Maekawa, T., 2001. Use of artificial neural network in the prediction of algal blooms. Water Research 35(8), 2022-(2028).

DOI: 10.1016/s0043-1354(00)00464-4

[8] Walter, M., Recknagel, F., Carpenter, C., Bormans, M., 2001. Predicting eutrophication effects in the Burrinjuck Reservoir (Australia) by means of the deterministic model SALMO and the recurrent neural network model ANNA. Ecological Modeling 146 (1-3), 97-114.

DOI: 10.1016/s0304-3800(01)00299-x

[9] Heyi Wang, Yi Gao, Zhaoan Xu, Weidong Xu. 2011 International Conference on Remote Sensing, Environment and Transportation Engineering. 984-988.

DOI: 10.1109/rsete.2011.5964444

[10] Olden, J.D., Joy, M.K., Death, R.G., 2004. An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol. Model. 178, 389-397.

DOI: 10.1016/j.ecolmodel.2004.03.013

[11] Jeong, K. -S., Kim, D. -K., Joo, G. -J., 2006. River phytoplankton prediction model by Artificial Neural Network: model performance and selection of input variables to predict time-series phytoplankton proliferations in a regulated river system. Ecol. Inform. 1, 235-245.

DOI: 10.1016/j.ecoinf.2006.04.001

[12] Hansel-welch, N., Butler, M.G., Carlson, T.J., Hanson, M.A., 2003. Changes in macrophyte community structure in Lake Christina (Minnesota), a large shallow lake, following biomanipulation. Aquatic Botany 75, 323-337.

DOI: 10.1016/s0304-3770(03)00002-0

[13] Tan, X., Kong, F.X., Zeng, Q.F., Cao, H.S., Qian, S.Q., Zhang, M., 2009. Seasonal variation of Microcystis in Lake Taihu and its relationships with environmental factors. Journal of Environmental Sciences 21, 892-899.

DOI: 10.1016/s1001-0742(08)62359-1

[14] Qiao Shuliang, Jin man, Chen Guoping, Zou Shan. Calculation method and characteristics of wind-wave in lake. Hydro-Science and Engineering. 1996(3), 189-198.

[15] Marcel Bottema, Gerbrant Ph. van Vledder. A ten-year data set for fetch- and depth-limited wave growth. Coastal Engineering 56 (2009) , 703-725.

DOI: 10.1016/j.coastaleng.2009.01.012

[16] Hu,W., Pu,P., Qin,B., 1998. A three-dimensional numerical simulation on the dynamics in Taihu Lake, China(I): the water level and the current during the 9711 typhoon process.J. LakeSci. 4, 17-25(in Chinese with English abstract).

DOI: 10.18307/1998.0403

[17] Vanderpoorten, A., Palm, R., 1998. Canonical variables of aquatic bryophyte combinations for predicting water trophic level. Hydrobiologia 386, 85-93.

[18] Recknagel, F., French, M., Harkonen, P., Yabunaka, K. -I., 1997. Artificial neural network approach for modeling and prediction of algal blooms. Ecol. Model. 96, 11-28.

DOI: 10.1016/s0304-3800(96)00049-x

[19] Tarassenko, L., 1998. A Guide to Neural Computing Applications. Arnold Publishers, London.

[20] Hecht-Nielsen, R., 1987. Kolmogorov's mapping neural network existence theorem. Proceedings of 1st IEEE International Joint Conference of Neural Networks. Institute of Electrical and Electronics Engineers, New York, NY.

[21] Jeong, K.S., Joo, G.J., Kim, H.W., Ha, K., Recknagel, F., 2001. Prediction and elucidation of algal dynamics in the Nakdong River (Korea) by means of a recurrent artificial neural network. Ecological Modeling 146, 115-129.

DOI: 10.1016/s0304-3800(01)00300-3

[22] Zar, J.H., 1984. Biostatistical Analysis, 2nd edition. Prentice-Hall, NJ, p.718.

[23] Zhu Yongchun, Cai Qiming. The dynamic research of the influence of wind field on the migration of algae in Taihu Lake. [J] JOURNALOFLAKESCIENCES 1997, 6: 152-158.

DOI: 10.18307/1997.0210

[24] ZHANG Yi-min, ZHANG Yong-chun et. The influence of lake hydrodynamics on blue algal growth. [J] China Environmental Science. 2007, 27(5)：707-711.