Abstract
In this work, time series neural networks were used to predict the occurrence of toxic cyanobacterial blooms in Crestuma Reservoir, which is an important potable water supply for the Porto region, located in the north of Portugal. These models can potentially be used to provide water treatment plant operators with an early warning for developing cyanobacteria blooms. Physical, chemical, and biological parameters were collected at Crestuma Reservoir from 1999 to 2002. The data set was then divided into three independent time series, each with a fortnightly periodicity. One training series was used to “teach” the neural networks to predict results. Another series was used to verify the results, and to avoid over-fitting of the data. An additional independently collected data series was then used to test the efficacy of the model for predicting the abundance of cyanobacteria. All of the models tested in this study incorporated a prediction time (look-ahead parameter) equal to the sampling interval (two weeks). Various lag periods, from 2 to 52 weeks, were also investigated. The best model produced in this study provided the following correlations between the target and forecast values in the training, verification, and validation series: 1.000 (P = 0.000), 0.802 (P = 0.000), and 0.773 (P = 0.001), respectively. By applying this model to the three-year data set, we were able to predict fluctuations in cyanobacteria abundance in the Crestuma Reservoir, with a high level of precision. By incorporating a lag-period of eight weeks, we were able to detect secondary fluctuations in cyanobacterial abundance over the annual cycle.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Literature Cited
Bishop C. 1995. Neural networks for pattern recognition. Oxford University Press, Oxford, 482 pp
Bobbin J., F. Recknagel. 2001a. Inducing explanatory rules for the prediction of algal blooms by genetic algorithms. Environmental International 27:237–242
Bobbin J., F. Recknagel. 2001b. Knowledge discovery for prediction and explanation of blue-green algal dynamics in lakes by evolutionary algorithms. Ecological Modelling 146:253–262
Ferreira F. M. B., J. M. F. Soler, M. L. Fidalgo, P. Fernández-Vila. 2001. PSP toxins from Aphanizomenon flos-aquae (cyanobacteria) collected in the Crestuma-Lever reservoir (Douro river, northern Portugal). Toxicon 39(6):757–761
French M., F. Recknagel. 1994. Modelling of algal blooms in freshwaters using artificial neural networks. in Zaneti P. (Eds.). Computer techniques in environmental studies V. Environmental systems, vol. II. Computational Mechanics Publications, Boston. Pages 87–94
Haykin S. 1999. Neural networks: a comprehensive foundation, 2nd edition. Prentice-Hall, Inc., New Jersey, 842 pp
Hornik, K. 1991. Approximation capability of multilayer feedforward networks. Neural Networks 4:251–257
Jeong K.-S., G.-J. Joo, H.-W Kim, K. Ha, F. Recknagel. 2001. Prediction and elucidation of phytoplankton dynamics in the Nakdong River (Korea) by means of a recurrent artificial neural network. Ecological Modelling 146(1-3):115–129
Karul C., S. Soyupak, C. Yurteri. 1999. Neural network models as a management tool in lakes. Hydrobiologia 408/409:139–144
Karul C., S. Soyupak, A. F. Çilesiz, N. Akbay, E. Germen. 2000. Case studies on the use of neural networks in eutrophication modelling. Ecological Modelling 134:145–152
Maier H. G., G. C. Dandy. 1998. The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study. Environmental Modelling and Software 13:193–209
Maier H. G., G. C. Dandy. 2000. Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environmental Modelling and Software 15:101–124
Maier H. G., G. C. Dandy. 2001. Neural network based modelling of environmental variables: a systematic approach. Mathematical and Computer Modelling 33:669–682
Maier H. G., G. C. Dandy, M. Burch. 1998. Use of artificial networks for modelling cyanobacteria Anabaena spp. in the River Murray, South Australia. Ecological Modelling 105:257–272
Maier H. G., T. Sayed, B. J. Lence. 2001. Forecasting cyanobacterium Anabaena spp. in the River Murray, South Australia, using B-spline neurofuzzy models. Ecological Modelling 146:85–96
Moss B. 1998. Ecology of fresh waters: Man and medium, past and future. 3rd edition. Blackwell Science, Oxford, 557 pp
Patterson D. 1996. Artificial neural networks: Theory and applications. Prentice Hall, Singapore
Qi M., G. P. Zhang. 2001. An investigation of model selection criteria for neural network time series forecasting. European Journal of Operational Research 132(3):666–680
Recknagel F. 2001. Applications of machine learning to ecological modelling. Ecological Modelling 146:303–310
Recknagel F., M. French, P. Harkonen, K.-I. Yabunaka. 1997. Artificial neural network approach for modelling and prediction of algal blooms. Ecological Modelling 96:11–28
Scardi M. 2001. Advances in neural network modelling of phytoplankton primary production. Ecological Modelling 146:33–45
Scardi M., L. Harding. 1999. Developing an empirical model of phytoplankton primary production: a neural network case study. Ecological Modelling 120:213–223
Schultz A., R. Wieland, G. Lutze. 2000. Neural networks in agroecological modelling: stylish application or helpful tool? Computers and Electronics in Agriculture 29:73–97
Speckt D. F. 1991. A generalized regression neural network. IEEE Transactions on Neural Networks 2(6):568–576
Statsoft. 2000. STATISTICA Neural Networks (Release 4.0 F), Tulsa, OK
Statsoft. 2001. STATISTICA (Version 6) Tulsa, OK
Vasconcelos V. M., W. Evans, W. W. Carmichael, M. Namikoshi. 1993. Isolation of microcystin-LR from a Microcystis (Cyanobacteria) bloom collected in the drinking water reservoir for Porto, Portugal. Journal of Environmental Science and Health 28(9):2081–2094
Wei B., N. Sugiura, T. Maekawa. 2001. Use of artificial neural network in the prediction of algal blooms. Water Research 35(8):2022–2028
Whigham P. A., F. Recknagel. 2001a. Predicting chlorophyll-a in freshwater lakes by hybridising process-based models and genetic algorithms. Ecological Modelling 146:243–251
Whigham P. A., F. Recknagel. 2001b. An inductive approach to ecological time series modelling by evolutionary computation. Ecological Modelling 146:275–287
Whitehead P. G., A. Howard, C. Arulmani. 1997. Modelling algal growth and transport in rivers: a comparison of time series analysis, dynamic mass balance and neural network techniques. Hydrobiologia 349:39–46
Yun S.-Y., S. Namkoong, J.-H. Rho, S.-W. Shin, J.-U. Choi. 1998. A perfomance evaluation of neural network models in traffic volume forecasting. Mathematical and Computer Modelling 27(9–11):293–310
Zhang G. P., M. Y. Hu. 1998. Neural network forecasting of the British pound/US dollar exchange rate. Omega, International Journal of Management Science 26(4):495–506
Zhang G. P., B. E. Patuwo, M. Y. Hu. 1998. Forecasting with artificial networks: The state of the art. International Journal of forecasting 14:35–62
Zhang G. P., B. E. Patuwo, M. Y. Hu. 2001. A simulation study of artificial neural networks for nonlinear time-series forecasting. Computers and Operation Research 28:381–396
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Teles, L.O., Vasconcelos, V., Teles, L.O. et al. Time Series Forecasting of Cyanobacteria Blooms in the Crestuma Reservoir (Douro River, Portugal) Using Artificial Neural Networks. Environmental Management 38, 227–237 (2006). https://doi.org/10.1007/s00267-005-0074-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00267-005-0074-9