Advertisement

Predicting Patterns In Spatial Ecology Using Neural Networks: Modelling Colonisation of New Zealand Fur Seals

  • Corey J. A. Bradshaw
  • Martin Purvis
  • Rumen Raykov
  • Qinqing Zhou
  • Lloyd S. Davis
Part of the IFIP — The International Federation for Information Processing book series (IFIPAICT, volume 39)

Abstract

Conventional mathematical models for ecological processes are often complex and restricted in their predictive capability through the non-linear and non-gaussian properties of the input data. In this paper we discuss the capability of an artificial neural network (ANN) model to predict the colonisation potential of New Zealand fur seals (Arctocephalus forsteri) around South Island, New Zealand. We used the distribution of food sources, sea configuration and coastline terrain to predict the potential condition of pups for coastline segments around South Island. We suggest that ANNs can be used effectively in combination with geographic information systems for ecological modelling.

Key words

ecology neural networks spatial modelling fur seals 

References

  1. Baran, P., S. Lek, M. Delacoste, and A. Belaud. 1996. Stochastic models that predict trout population density or biomass on a mesohabitat scale. Hydrobiologia 337: 1–9.CrossRefGoogle Scholar
  2. Guégan, J.-F., S. Lek, and T. Oberdorff. 1998. Energy availability and habitat heterogeneity predict global riverine fish diversity. Nature 391: 382–384.CrossRefGoogle Scholar
  3. Homik, K., M. Stinchcombe, and H. White. 1989. Multilayer feedforward networks are universal approximators. Neural Networks 2: 359–366.CrossRefGoogle Scholar
  4. Laws, R. M., Ed. 1993. Antarctic seals: research methods and techniques. Cambridge University Press, Cambridge.Google Scholar
  5. Lek, S., M. Delacoste, P. Baran, 1. Dimopoulos, J. Lauga, and S. Aulagnier. 1996. Application of neural networks to modelling nonlinear relationships in ecology. Ecological Modelling 90: 39–52.Google Scholar
  6. Liu, H. & Tan, S. T. (1995) X2R: A Fast Rule Generator. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (SMC’95), Vancouver, Canada, pp. 631–1635.Google Scholar
  7. Mastrorillo, S., S. Lek, and F. Dauba. 1997. Predicting the abundance of minnow Phoxinus phoxinus (Cyprinidae) in the River Ariège ( France) using artificial neural networks. Aquatic Living Resources 10: 169–176.Google Scholar
  8. NIWA - the New Zealand National Institute of Water and Atmospheric Research, Auckland, New Zealand.Google Scholar
  9. Purvis, M., Kasabov, N., Benwell, G., Zhou, Q., and Zhang, F., “Neuro-fuzzy Methods for Environmental Modelling”, in Environmental Software Systems 2, Denzer, R., Swayne, D. A., and Schimak, G., (eds.), Chapman and Hall, London (1997) 30–37.CrossRefGoogle Scholar
  10. Scardi, M. 1996. Artificial neural networks as empirical models for estimating phytoplankton production. Marine Ecological Progress Series 139: 289–299.CrossRefGoogle Scholar
  11. Schreer, J. F., R. J. O’Hara Hines and K. M. Kovacs. 1998. Classification of dive profiles: a comparison of statistical clustering techniques and unsupervised artificial neural networks. Journal of Agricultural, Biological, and Environmental Statistics 3: 383–404.Google Scholar
  12. Tortell, P., ed. 1981. The New Zealand Atlas of Coastal Resources. P.D. Hasselberg Government Printer, Wellington.Google Scholar
  13. Wanless, S., P. J. Bacon, M. P. Harris, A. D. Webb, S. P. R. Greenstreet, and A. Webb. 1997. Modelling environmental and energetic effects on feeding performance and distribution of shags ( Phalacrocorax aristotelis) integrating telemetry, geographical information systems, and modelling techniques. ICES Journal of Marine Science 54: 524–544.Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2000

Authors and Affiliations

  • Corey J. A. Bradshaw
    • 1
  • Martin Purvis
    • 2
  • Rumen Raykov
    • 2
  • Qinqing Zhou
    • 2
  • Lloyd S. Davis
    • 1
  1. 1.Department of ZoologyUniversity of OtagoDunedinNew Zealand
  2. 2.Department of Information ScienceUniversity of OtagoDunedinNew Zealand

Personalised recommendations