Machine Learning a Probabilistic Network of Ecological Interactions

  • Alireza Tamaddoni-Nezhad
  • David Bohan
  • Alan Raybould
  • Stephen H. Muggleton
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7207)

Abstract

In this paper we demonstrate that machine learning (using Abductive ILP) can generate plausible and testable food webs from ecological data. In this approach, unlike previous applications of Abductive ILP, the abductive predicate ‘eats’ is entirely undefined before the start of the learning. We also explore a new approach, called Hypothesis Frequency Estimation (HFE), for estimating probabilities for hypothetical ‘eats’ facts based on their frequency of occurrence when randomly sampling the hypothesis space. The results of cross-validation tests suggest that the trophic networks with probabilities have higher predictive accuracies compared to the networks without probabilities. The proposed trophic networks have been examined by domain experts and comparison with the literature shows that many of the links are corroborated by the literature. In particular, links ascribed with high frequency are shown to correspond well with those having multiple references in the literature. In some cases novel high frequency links are suggested, which could be tested.

Keywords

Predictive Accuracy Ecological Data Ecological Interaction Inductive Logic Programming Multiple Reference 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alexander, K.N.A.: The invertebrates of living and decaying timber in Britain and Ireland–a provisional annotated checklist. English Nature Research Reports 467, 1–142 (2002)Google Scholar
  2. 2.
    Bauer, T.: Prey-capture in a ground-beetle larva. Animal Behaviour 30(1), 203–208 (1982)CrossRefGoogle Scholar
  3. 3.
    Bell, J.R., Andrew King, R., Bohan, D.A., Symondson, W.O.C.: Spatial cooccurrence networks predict the feeding histories of polyphagous arthropod predators at field scales. Ecography 33(1), 64–72 (2010)CrossRefGoogle Scholar
  4. 4.
    Berg, K.: The role of detrital subsidies for biological control by generalist predators evaluated by molecular gut content analysis. PhD thesis, Universitäts-und Landesbibliothek Darmstadt (2007)Google Scholar
  5. 5.
    Desender, K., Pollet, M.: Ecological data on clivina fossor (coleoptera, carabidae) from a pasture ecosystem. ii. reproduction, biometry, biomass, wing polymorphism and feeding ecology. Rev. Ecol. Biol. Sol. 22(2), 233–246 (1985)Google Scholar
  6. 6.
    Dinter, A.: Intraguild predation between erigonid spiders, lacewing larvae and carabids. Journal of Applied Entomology 122(1-5), 163–167 (1998)CrossRefGoogle Scholar
  7. 7.
    Lattin, J.D.: Bionomics of the nabidae. Annual Review of Entomology 34(1), 383–400 (1989)CrossRefGoogle Scholar
  8. 8.
  9. 9.
    Pons, X., Lumbierres, B., Albajes, R.: Heteropterans as aphid predators in inter-mountain alfalfa. European Journal of Entomology 106(3), 369–378 (2009)Google Scholar
  10. 10.
    Schaefer, C.W., Panizzi, A.R.: Heteroptera of economic importance. CRC (2000)Google Scholar
  11. 11.
    Sunderland, K.D.: The diet of some predatory arthropods in cereal crops. Journal of Applied Ecology 12(2), 507–515 (1975)CrossRefGoogle Scholar
  12. 12.
    Sunderland, K.D., Lovei, G.L., Fenlon, J.: Diets and reproductive phenologies of the introduced ground beetles harpalus-affinis and clivina-australasiae (coleoptera, carabidae) in new-zealand. Australian Journal of Zoology 43(1), 39–50 (1995)CrossRefGoogle Scholar
  13. 13.
    Toft, S.: The quality of aphids as food for generalist predators: implications for natural control of aphids. European Journal of Entomology 102(3), 371 (2005)Google Scholar
  14. 14.
    Turner, B.D.: Predation pressure on the arboreal epiphytic herbivores of larch trees in southern england. Ecological Entomology 9(1), 91–100 (1984)CrossRefGoogle Scholar
  15. 15.
    Warner, D.J., Allen-Williams, L.J., Warrington, S., Ferguson, A.W., Williams, I.H.: Mapping, characterisation, and comparison of the spatio-temporal distributions of cabbage stem ea beetle (psylliodes chrysocephala), carabids, and collembolan in a crop of winter oilseed rape (brassica napus). Entomologia Experimentalis et applicata 109(3), 225–234 (2003)CrossRefGoogle Scholar
  16. 16.
    Weber, D.C., Lundgren, J.G.: Assessing the trophic ecology of the coccinellidae: their roles as predators and as prey. Biological Control 51(2), 199–214 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Alireza Tamaddoni-Nezhad
    • 1
  • David Bohan
    • 2
    • 3
  • Alan Raybould
    • 4
  • Stephen H. Muggleton
    • 1
  1. 1.Department of ComputingImperial College LondonLondonUK
  2. 2.Rothamsted ResearchHarpendenUK
  3. 3.INRA, UMR 1210 Biologie et Gestion des AdventicesDijonFrance
  4. 4.Syngenta Ltd.BracknellUK

Personalised recommendations