Development and Application of Predictive River Ecosystem Models Based on Classification Trees and Artificial Neural Networks

  • P. Goethals
  • A. Dedecker
  • W. Gabriels
  • N. De Pauw


Prediction of freshwater organisms based on machine learning techniques is becoming more and more reliable due to the availability of appropriate datasets and modelling techniques. Artificial neural networks (Lek and Guegan 1999), fuzzy logic (Barros et al. 2000), evolutionary algorithms (Caldarelli et al. 1998), cellular automata (Gronewold and Sonnenschein 1998), etc. proved to be powerful tools to perform ecological modelling, especially when large datasets are involved. Models have several interesting applications in river management. They allow for a better interpretation of the results, easing the cause-allocation of the actual river status and increasing the insight needed to improve assessment systems (Fig. 6.1.). Models also allow for simulating the effect of potential management options and thus supporting decision-making. The development of effective and efficient monitoring networks based on models is probably another important advantage.


Artificial Neural Network Classification Tree Macroinvertebrate Community Tenfold Cross Validation River Restoration 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. AMINAL (1999) Control of sediment transport in unnavigable watercourses as part of integrated water management: Zwalm river basin project. AMINAL, Ghent (in Dutch)Google Scholar
  2. Barros LC, Bassanezi RC, Tonelli PA (2000) Fuzzy modelling in population dynamics. Ecological Modelling, 128, 27–33CrossRefGoogle Scholar
  3. Breimann L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Pacific Grove,WadsworthGoogle Scholar
  4. Caldarelli G, Higgs PG, McKane AJ (1998) Modelling coevolution in multispecies communities. Journal of Theoretical Biology, 193, 345–358CrossRefGoogle Scholar
  5. Carchon P, De Pauw N (1997) Development of a methodology for the assessment of surface waters. Study by order of the Flemish Environmental Agency (VMM). Ghent University, Laboratory of Environmental Toxicology and Aquatic Ecology, Gent, 55p (in Dutch)Google Scholar
  6. Cestnik B, Kononenko I, Bratko I (1987) ASSISTANT 86: A knowledge elicitation tool for sophisticated users. In: Bratko, I. & Lavrak, N. Progress in machine learning. Sigma Press, WilmslowGoogle Scholar
  7. Dedecker A (2001) Modelling of macroinvertebrate communities in the Zwalm River basin by means of artificial neural networks. M. Eng. thesis, Ghent University, Faculty of Applied Biological Sciences, in preparation (in Dutch)Google Scholar
  8. D’Heygere T, Goethals P, De Pauw N (2001) Application of genetic algorithms for input variables selection of decision tree models predicting mollusca in unnavigable Flemish watercourses. Mededelingen Faculteit Landbouwkundige en Toegepaste Biologische Wetenschappen, Ghent University, Gent, Belgium (in press)Google Scholar
  9. Demuth H, Beale M (1998) Neural Network Toolbox for use with MATLAB. User’s guide. Version 3.0. The Mathworks, Inc., Natick, USAGoogle Scholar
  10. De Pauw N (2000) Using RIVPACS as a modeling tool to predict the impacts of environmental changes. p. 311–314. In: Wright, J.F., Sutcliffe, D.W., & Furse, M.T. Assessing the biological quality of fresh waters: RIVPACS and other techniques. FBA, Ambleside (UK)Google Scholar
  11. De Pauw N, Vanhooren G (1983) Method for biological assessment of watercourses in Belgium. Hydrobiologia, 100, 153–168CrossRefGoogle Scholar
  12. De Pauw N, Vannevel R (1993) Macroinvertebrates and water quality. Dossiers Stichting Leefmilieu 11: Stichting Leefmilieu, Antwerp (in Dutch)Google Scholar
  13. Dzeroski S, Grbovic J, Walley WJ (1997) Machine learning applications in biological classification of river water quality, p. 429–448. In: Michalski, R.S., Bratko, I. & Kubat, M. Machine learning and data mining: methods and applications. John Wiley & Sons Ltd., New YorkGoogle Scholar
  14. Gabriels W, Goethals PLM, Heylen S, De Cooman W, De Pauw N (2000) Modelling benthic macro-invertebrate communities in Flanders using artificial neural networks. IWA, Proc. Watermatex 2000 Symposium, Ghent. p. 1.143–1.146Google Scholar
  15. Goethals P, De Pauw N (2001) Development of a concept for integrated ecological river assessment in Flanders, Belgium. Journal of Limnology (in press)Google Scholar
  16. Goethals P, Dzeroski S, Vanrolleghem P, De Pauw N (2001) Prediction of benthic macroinvetebrate taxa (Asellidae and Tubificidae) in watercourses of Flanders by means of classification trees. Paper submitted at the IWA 2 nd World Water Congress Berlin 2001Google Scholar
  17. Gronewold A, Sonnenschein M (1998) Event-based modelling of ecological systems with asynchronous cellular automata. Ecological Modelling, 108, 37–52CrossRefGoogle Scholar
  18. Lauryssen F, Tack F, Verloo M (1994) Nitrogen transport in the Zwalm river basin. Water, 75, 46–49 (in Dutch)Google Scholar
  19. Lek S, Guegan JF (1999) Artificial neural networks as a tool in ecological modelling, an introduction. Ecological Modelling, 120, 65–73CrossRefGoogle Scholar
  20. NBN (1984) Biological water quality: determination of the biotic index based on aquatic macroinvertebrates, NBN T92–402. Institut Belge de Normalisation (IBN) (in Dutch and French)Google Scholar
  21. Quinlan JR (1986) Induction of decision trees. Machine Learning, 1(1), 81–106Google Scholar
  22. Quinlan JR (1993) C4.5: Programs for machine learning. Morgan Kaufmann, San FranciscoGoogle Scholar
  23. Schleiter IM, Borchardt D, Wagner R, Dapper T, Schmidt KD, Schmidt HH, Werner H (1999) Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks. Ecological Modelling, 120, 271–286CrossRefGoogle Scholar
  24. Soresma (2000) Environmental impact assessment report on the development of fish migration channels and natural overflow systems in the Zwalm river basin. Soresma Advies- en Ingenieursbureau, Antwerp (in Dutch)Google Scholar
  25. VMM (2000) Water quality — water discharges 1999. Flemish Environmental Agency, VMM, Erembodemgem (in Dutch)Google Scholar
  26. Walley WJ, Fontama VN (1998) Neural network predictors of average score per taxon and number of families at unpolluted sites in Great Britain. — Water Research, 32, 613–622CrossRefGoogle Scholar
  27. Walley WJ, Fontama VN (2000) New approaches to river quality classification based upon artificial intelligence. p. 263–280. In: Wright, J.F., Sutcliffe, D.W., & Furse, M.T. Assessing the biological quality of fresh waters: RIVPACS and other techniques. FBA, Ambleside (UK)Google Scholar
  28. Witten IH, Frank E (2000) Data mining: practical machine learning tooals and techniques with Java implementations. Morgan Kaufmann Publishers, San FranciscoGoogle Scholar
  29. Wright JF, Sutcliffe DW, Furse MT (2000) Assessing the biological quality of fresh waters: RIVPACS and other techniques. FBA, Ambleside (UK). pp 373Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • P. Goethals
  • A. Dedecker
  • W. Gabriels
  • N. De Pauw

There are no affiliations available

Personalised recommendations