Discovering Ecosystem Models from Time-Series Data

  • Dileep George
  • Kazumi Saito
  • Pat Langley
  • Stephen Bay
  • Kevin R. Arrigo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2843)


Ecosystem models are used to interpret and predict the interactions of species and their environment. In this paper, we address the task of inducing ecosystem models from background knowledge and time-series data, and we review IPM, an algorithm that addresses this problem. We demonstrate the system’s ability to construct ecosystem models on two different Earth science data sets. We also compare its behavior with that produced by a more conventional autoregression method. In closing, we discuss related work on model induction and suggest directions for further research on this topic.


Generic Process Autoregressive Model Ecosystem Model Modeling Task Minimum Description Length 
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. Arrigo, K.R., Worthen, D.L., Robinson, D.H.: A coupled ocean-ecosystem model of the Ross Sea. Part 2: Phytoplankton taxonomic variability and primary production. Journal of Geophysical Research (in press)Google Scholar
  2. Box, G.E.P., Cox, D.R.: An analysis of transformations. Journal of the Royal Statistical Society, Series B 26, 211–252 (1964)zbMATHMathSciNetGoogle Scholar
  3. Bradley, E., Easley, M., Stolle, R.: Reasoning about nonlinear system identification. Artificial Intelligence 133, 139–188 (2001)zbMATHCrossRefGoogle Scholar
  4. Josephson, J.R.: Smart inductive generalizations are abductions. In: Flach, P.A., Kakas, A.C. (eds.) Abduction and induction, Kluwer, Dordrecht (2000)Google Scholar
  5. Jost, C., Adiriti, R.: Identifying predator-prey processes from time-series. Theoretical Population Biology 57, 325–337 (2000)zbMATHCrossRefGoogle Scholar
  6. Koza, J., Mydlowec, W., Lanza, G., Yu, J., Keane, M.: Reverse engineering and automatic synthesis of metabolic pathways from observed data using genetic programming. In: Pacific Symposium on Biocomputing, vol. 6, pp. 434–445 (2001)Google Scholar
  7. Langley, P., George, D., Bay, S., Saito, K.: Robust induction of process models from time-series data. In: Proceedings of the Twentieth International Conference on Machine Learning, AAAI Press, Washington (in press)Google Scholar
  8. Luenberger, D.G.: Linear and nonlinear programming. Addison- Wesley, Reading (1984)zbMATHGoogle Scholar
  9. Morris, W.F.: Disentangling effects of induced plant defenses and food quantity on herbivores by fitting nonlinear models. American Naturalist 150, 299–327 (1997)CrossRefGoogle Scholar
  10. Richmond, B., Peterson, S., Vescuso, P.: An academic user’s guide to STELLA. Lyme, NH: High Performance Systems (1987)Google Scholar
  11. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel distributed processing, MIT Press, Cambridge (1986)Google Scholar
  12. Saito, K., Nakano, R.: Law discovery using neural networks. In: Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, pp. 1078–1083. Morgan Kaufmann, Yokohama (1997)Google Scholar
  13. Schneider, T., Neumaier, A.: Algorithm 808: ARFIT – A Matlab package for the estimation of parameters and eigenmodes of multivariate autoregressive models. ACM Transactions on Mathematical Software 27, 58–65 (2001)zbMATHCrossRefGoogle Scholar
  14. Todorovski, L., Džeroski, S.: Declarative bias in equation discovery. In: Proceedings of the Fourteenth International Conference on Machine Learning, pp. 376–384. Morgan Kaufmann, San Francisco (1997)Google Scholar
  15. Veilleux, B.G.: An analysis of the predatory interaction between Paramecium and Didinium. Journal of Animal Ecology 48, 787–803 (1979)CrossRefGoogle Scholar
  16. Washio, T., Motoda, H., Niwa, Y.: Enhancing the plausibility of law equation discovery. In: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 1127–1134. Morgan Kaufmann, Stanford (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Dileep George
    • 1
  • Kazumi Saito
    • 2
  • Pat Langley
    • 1
  • Stephen Bay
    • 1
  • Kevin R. Arrigo
    • 3
  1. 1.Computational Learning Laboratory, CSLIStanford UniversityStanfordUSA
  2. 2.NTT Communication Science LaboratoriesSoraku, KyotoJapan
  3. 3.Department of GeophysicsStanford UniversityStanfordUSA

Personalised recommendations