Ecological Informatics for the Prediction and Management of Invasive Species

  • Susan P. WornerEmail author
  • Muriel GevreyEmail author
  • Takayoshi IkedaEmail author
  • Gwenaël LedayEmail author
  • Joel PittEmail author
  • Stefan SchliebsEmail author
  • Snjezana SolticEmail author
Part of the Springer Handbooks book series (SHB)


Ecologists face rapidly accumulating environmental data form spatial studies and from large-scale field experiments such that many now specialize in information technology. Those scientists carry out interdisciplinary research in what is known as ecological informatics. Ecological informatics is defined as a discipline that brings together ecology and computer science to solve problems using biologically-inspired computation, information processing, and other computer science disciplines such as data management and visualization. Scientists working in the discipline have research interests that include ecological knowledge discovery, clustering, and forecasting, and simulation of ecological dynamics by individual-based or agent-based models, as well as hybrid models and artificial life. In this chapter, ecological informatics techniques are applied to answer questions about alien invasive species, in particular, species that pose a biosecurity threat in a terrestrial ecological setting. Biosecurity is defined as the protection of a regionʼs environment, flora and fauna, marine life, indigenous resources, and human and animal health. Because biological organisms can cause billions of dollars of impact in any country, good science, systems, and protocols that underpin a regulatory biosecurity system are required in order to facilitate international trade. The tools and techniques discussed in this chapter are designed to be used in a risk analysis procedure so that agencies in charge of biosecurity can prioritize scarce resources and effort and be better prepared to prevent unexpected incursions of dangerous invasive species. The methods are used to predict, (1) which species out of the many thousands might establish in a new area, (2) where those species might establish, and, (3) where they might spread over a realistic landscape so that their impact can be determined.


Geographic Information System Gypsy Moth Relative Operating Characteristic Well Match Unit True Skill Statistic 
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.



artificial neural network


dynamic neuro-fuzzy inference system


evolving clustering method


geographical information system


global navigation system


individual-based model


modular dispersal in GIS


multilayer perceptron


naive Bayesian classifier


neural network


quantum-inspired spiking neural network


receiver operating characteristic


species distribution model


self-organizing map


support vector


support vector machine


true skill statistic


conditional tree


linear discriminant analysis


naive Bayes


quadratic discriminant analysis


support vector machine


  1. 35.1.
    A. Ellis, K.S. Delaplane: Effects of nest invaders on honey bee (Apis mellifera) pollination efficacy, Agric. Ecosyst. Environ. 127, 201–206 (2008)CrossRefGoogle Scholar
  2. 35.2.
    T.D. Breeze, A.P. Bailey, K.G. Balcombe, S.G. Potts: Pollination services in the UK: How important are honeybees?, Agric. Ecosyst. Environ. 142, 137–143 (2011)CrossRefGoogle Scholar
  3. 35.3.
    M. Gevrey, S.P. Worner: Prediction of global distribution of insect pest species in relation to climate by using an ecological informatics method, J. Econ. Entomol. 99, 979–986 (2006)CrossRefGoogle Scholar
  4. 35.4.
    F. Recknagel: Ecological Informatics: Understanding Ecology by Biologically Inspired Computation (Springer, New York 2002)Google Scholar
  5. 35.5.
    F. Recknagel (Ed.): Ecological Informatics. Scope, Techniques and Applications, 2nd edn. (Springer, New York 2006) p. 496Google Scholar
  6. 35.6.
    S.P. Worner, M. Gevrey: Modelling global insect species assemblages to determine risk of Invasion, J. Appl. Ecol. 43, 858–867 (2006)CrossRefGoogle Scholar
  7. 35.7.
    M. Gevrey, S.P. Worner, N. Kasabov, J. Pitt, J.-L. Giraudel: Estimating risk of events using SOM models: A case study on invasive species establishment, Ecol. Model. 197, 361–372 (2006)CrossRefGoogle Scholar
  8. 35.8.
  9. 35.9.
    T. Kohonen: Self-organized formation of topologically correct feature maps, Biol. Cybern. 43, 59–69 (1982)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 35.10.
    T. Kohonen: Self-Organizing Maps (Springer, Berlin, Heidelberg 2001)CrossRefzbMATHGoogle Scholar
  11. 35.11.
    M.J. Watts, S.P. Worner: Estimating the risk of insect species invasion: Kohonen self-organising maps versus k-means clustering, Ecol. Model. 220, 821–829 (2009)CrossRefGoogle Scholar
  12. 35.12.
    D.R. Paini, S.P. Worner, M.B. Thomas, D.C. Cook: Using a self organising map to predict invasive species: Sensitivity to data errors and a comparison with expert opinion, J. Appl. Ecol. 47, 290–298 (2010)CrossRefGoogle Scholar
  13. 35.13.
    J. Pitt, J. Regniere, S.P. Worner: Risk assessment of gypsy moth, Lymantria dispar (L.) in New Zealand based on phenology modelling, Int. J. Biometeorol. 51, 295–305 (2006)CrossRefGoogle Scholar
  14. 35.14.
    W. Kresse, D. Danko (Eds.): Springer Handbook of Geographic Information (Springer, Berlin, Heidelberg 2012)Google Scholar
  15. 35.15.
    M. Kearney, B.L. Phillips, C.R. Tracy, K.A. Christian, G. Betts, W.P. Porter: Modelling species distributions without using species distributions: The cane toad in Australia under current and future climates, Ecography 31, 423–434 (2008)CrossRefGoogle Scholar
  16. 35.16.
    R.G. Pearson, T.P. Dawson: Predicting the impacts of climate change on the distribution of species: Are bioclimate envelope models useful?, Global Ecol. Biogeogr. 12, 361–371 (2003)CrossRefGoogle Scholar
  17. 35.17.
    A.T. Peterson: Predicting the geography of speciesʼ invasions via ecological niche modeling, Q. Rev. Biol. 78, 419–433 (2003)CrossRefGoogle Scholar
  18. 35.18.
    N. Roura-Pascual, C. Hui, T. Ikeda, G. Leday, D.M. Richardson, S. Carpintero, X. Espadaler, C. Gómez, B. Guénard, S. Hartley, P. Krushelnycky, P.J. Lester, M. McGeoch, S. Menke, J. Pedersen, J. Pitt, J. Reyes, N.J. Sanders, A.V. Suarez, Y. Touyama, D. Ward, P. Ward, J. Wetterer, S.P. Worner: Relative roles of climatic suitability and anthropogenic influence in determining the pattern of spread in a global invader, Proc. Natl. Acad. Sci. 108, 220–225 (2011)CrossRefGoogle Scholar
  19. 35.19.
    M.J. Watts, S.P. Worner: Comparing ensemble and cascaded neural networks that combine biotic and abiotic variables to predict insect species distribution, Ecol. Inform. 3, 354–366 (2008)CrossRefGoogle Scholar
  20. 35.20.
    I. Guyon, A. Elisseeff: An introduction to variable and feature selection, J. Mach. Learn. Res. 3, 1157–1182 (2003)zbMATHGoogle Scholar
  21. 35.21.
    S. Schliebs, M. Defoin-Platel, S. Worner, N. Kasabov: Quantum-Inspired Feature and Parameter Optimization of Evolving Spiking Neural Networks with a Case Study from Ecological Modelling, Proc. Int. Joint Conf. Neural Netw. (Atlanta, 2009) pp. 2833–2840Google Scholar
  22. 35.22.
    S. Schliebs, M.D. Platel, S.P. Worner, N. Kasabov: Integrated feature and parameter optimisation for an evolving spiking neural network: Exploring heterogeneous probabilistic models, Neural Netw. 22, 623–632 (2009)CrossRefGoogle Scholar
  23. 35.23.
    A.H. Hirzel, J. Hausser, D. Chessel, N. Perrin: Ecological-niche factor analysis: How to compute habitat-suitability maps without absence data?, Ecology 83, 2027–2036 (2002)CrossRefGoogle Scholar
  24. 35.24.
    D. Stockwell, D. Peters: The GARP modelling system: Problems and solutions to automated spatial prediction, Int. J. Geogr. Inf. Sci. 13, 143 (1999)CrossRefGoogle Scholar
  25. 35.25.
    R.M. Chefaoui, J.M. Lobo: Assessing the effects of pseudo-absences on predictive distribution model performance, Ecol. Model. 210, 478–486 (2008)CrossRefGoogle Scholar
  26. 35.26.
    S.P. Worner, T. Ikeda, G. Leday, M. Joy: Surveillance tools for freshwater invertebrates, Ministry Agriculture Forestry NZ, Biosecurity Technical Paper 2010/21, 112 (2010)Google Scholar
  27. 35.27.
    N.G. Gratz: Critical review of the vector status of Aedes albopictus, Med. Vet. Entomol. 18, 215–227 (2004)CrossRefGoogle Scholar
  28. 35.28.
    B. Scholköpf, J.C. Platt, J. Shawe-Taylor, A.J. Smola, R.C. Williamson: Estimating the support of a high-dimensional distribution, Neural Comput. 13, 1443–1471 (2001)CrossRefzbMATHGoogle Scholar
  29. 35.29.
    J.M. Drake, C. Randin, A. Guisan: Modelling ecological niches with support vector machines, J. Appl. Ecol. 43, 424–432 (2006)CrossRefGoogle Scholar
  30. 35.30.
    Q. Guo, M. Kelly, C.H. Graham: Support vector machines for predicting distribution of sudden oak death in California, Ecol. Model. 182, 75–90 (2005)CrossRefGoogle Scholar
  31. 35.31.
    W. Zuo, N. Lao, Y. Geng, K. Ma: GeoSVM: An efficient and effective tool to predict speciesʼ potential distributions, J. Plant Ecol. 1, 143–145 (2008)CrossRefGoogle Scholar
  32. 35.32.
    J.A. Hartigan, M.A. Wong: A k-means clustering algorithm, J. R. Stat. Soc. C 28, 100–108 (1979)zbMATHGoogle Scholar
  33. 35.33.
    P. Segurado, M.B. Araujo: An evaluation of methods for modelling species distributions, J. Biogeogr. 31, 1555–1568 (2004)CrossRefGoogle Scholar
  34. 35.34.
    J. Elith, C.H. Graham, R.P. Anderson, M. Dudík, S. Ferrier, A. Guisan, R.J. Hijmans, F. Huettmann, J.R. Leathwick, A. Lehmann, J. Li, L.G. LohmannL, B.A. Loiselle, G. Manion, C. Moritz, M. Nakamura, Y. Nakazawa, J.M. Overton, P.A. Townsend, S.J. Phillips, K. Richardson, R. Scachetti-Pereira, R.E. Schapire, J. Soberón, S. Williams, M.S. Wisz, N.E. Zimmermann: Novel methods improve prediction of speciesʼ distributions from occurrence data, Ecography 29, 129–151 (2006)CrossRefGoogle Scholar
  35. 35.35.
    V. Vapnik: The Nature of Statistical Learning Theory, 2nd edn. (Springer, Berlin, Heidelberg 1999)zbMATHGoogle Scholar
  36. 35.36.
    S. Lek, J.F. Guégan: Artificial neural networks as a tool in ecological modelling, An Introduction. Ecol. Model. 120, 65–73 (1999)CrossRefGoogle Scholar
  37. 35.37.
    L. Breiman: Random forests, Mach. Learn. 45, 5–32 (2001)CrossRefzbMATHGoogle Scholar
  38. 35.38.
    S.J. Mason, N.E. Graham: Areas beneath the relative operating characteristics (ROC) and relative operating levels (ROL) curves: Statistical significance and interpretation, Q. J. R. Meteorol. Soc. 128, 2145–2166 (2002)CrossRefGoogle Scholar
  39. 35.39.
    J.R. Landis, G.G. Koch: The measurement of observer agreement for categorical data, Biometrics 33, 159–174 (1977)MathSciNetCrossRefzbMATHGoogle Scholar
  40. 35.40.
    C. Furlanello, S. Merler, C. Chemini, A. Rizzoli: An Application of the Bootstrap 632 + Rule to Ecological Data, Neural Nets, Vol. WIRN-97 (MIT Press, Cambridge 1998)Google Scholar
  41. 35.41.
    O. Allouche, A. Tsoar, R. Kadmon: Assessing the accuracy of species distribution models: Prevalence, kappa and the true skill statistic (TSS), J. Appl. Ecol. 43, 1223–1232 (2006)CrossRefGoogle Scholar
  42. 35.42.
    J. Elith, J.R. Leathwick: Species distribution models: Ecological explanation and prediction across space and time, Annu. Rev. Ecol. Evol. Syst. 40, 677–697 (2009)CrossRefGoogle Scholar
  43. 35.43.
    S. Soltic, S. Pang, L. Peacock, S.P. Worner: Evolving computation offers potential for estimation of pest establishment, Int. J. Comput. Syst. Signals 5, 36–43 (2004)Google Scholar
  44. 35.44.
    N. Kasabov: Evolving Connectionist Systems (Springer, Berlin, Heidelberg 2002)zbMATHGoogle Scholar
  45. 35.45.
    N. Kasabov, Q. Song: Dynamic evolving neural-fuzzy inference system and its application for time-series prediction, IEEE Trans. Fuzzy Syst. 10, 144–154 (2002)CrossRefGoogle Scholar
  46. 35.46.
    J.P.W. Pitt, S.P. Worner, A.V. Suarez: Predicting Argentine ant spread over the Heterogeneous landscape using a spatially-explicit stochastic model, Ecol. Appl. 19, 1176–1186 (2009)CrossRefGoogle Scholar
  47. 35.47.
    R.A. Fisher: The wave of advance of advantageous genes, Ann. Eugen. 7, 355–369 (1937)CrossRefzbMATHGoogle Scholar
  48. 35.48.
    J.G. Skellam: Random dispersal in theoretical populations, Biometrika 38, 196–218 (1951)MathSciNetCrossRefzbMATHGoogle Scholar
  49. 35.49.
    E.E. Holmes: Are diffusion models too simple? A comparison with telegraph models of invasion, Am. Nat. 142, 403–419 (1993)CrossRefGoogle Scholar
  50. 35.50.
    R.H. Gardner, E.J. Gustafson: Simulating dispersal of reintroduced species within heterogeneous landscapes, Ecol. Model. 171, 339–358 (2004)CrossRefGoogle Scholar
  51. 35.51.
    S. Hein, B. Pfenning, T. Hovestadt, H.-J. Poethke: Patch density, movement pattern, and realised dispersal distances in a patch-matrix landscape – a simulation study, Ecol. Model. 174, 411–420 (2004)CrossRefGoogle Scholar
  52. 35.52.
    D. Rhind: A GIS research agenda, Int. J. GIS 2, 23–28 (1988)Google Scholar
  53. 35.53.
    M. Neteler, H. Mitasova: Open Source GIS: A GRASS GIS Approach, 2nd edn. (Kluwer Academic, Boston 2004)Google Scholar
  54. 35.54.
    E.C. Pielou: Biogeography (Wiley, New York 1979)Google Scholar
  55. 35.55.
    A.D. Cliff, P. Haggett, J.D. Ord, G.R. Versey: Spatial Diffusion (Cambridge Univ. Press, Cambridge 1981)Google Scholar
  56. 35.56.
    D. Mollison: Spatial contact models for ecological and epidemic spread, J. R. Stat. Soc. B 39, 283–326 (1977)MathSciNetzbMATHGoogle Scholar
  57. 35.57.
    J.S. Clark, M. Lewis, L. Horvath: Invasion by extremes: Population spread with variation in dispersal and reproduction, Am. Nat. 157, 537–554 (2001)CrossRefGoogle Scholar
  58. 35.58.
    J. von Neumann: The general and logical theory of automata. In: Cerebral Mechanisms in Behavior – The Hixon Symposium, ed. by L.A. Jeffress (Wiley, New York 1951)Google Scholar
  59. 35.59.
    A.J. Hoffman, R.R. Singleton: Moore graphs with diameter 2 and 3, IBM J. Res. Dev. 5, 497–504 (1960)MathSciNetCrossRefzbMATHGoogle Scholar
  60. 35.60.
    M. Peng: Spatio-Temporal Modelling of Biological Invasions. Ph.D. Thesis (University of Auckland, NZ 2000)Google Scholar
  61. 35.61.
    S. Hartley, P.J. Lester: Temperature-dependent development of the Argentine ant, Linepithema humile (Mayr) (Hymenoptera: Formicidae): A degree-day model with implications for range limits in New Zealand, NZ Entomol. 26, 91–100 (2003)CrossRefGoogle Scholar
  62. 35.62.
    S. Worner: Use of models in applied entomology: The need for perspective, Environ. Entomol. 20(3), 768–773 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2014

Authors and Affiliations

  1. 1.Bio-Protection Research CentreLincoln UniversityLincolnNew Zealand
  2. 2.Chesapeake Biological LaboratoryUniversity of MarylandSolomonsUSA
  3. 3.Deanʼs DepartmentUniversity of OtagoWellingtonNew Zealand
  4. 4.Department of MathematicsVrije Universiteit AmsterdamAmsterdamThe Netherlands
  5. 5.c/0 Bio-Protection Research CentreLincoln UniversityLincolnNew Zealand
  6. 6.School of Computing and Mathematical SciencesAuckland University of TechnologyAucklandNew Zealand
  7. 7.Engineering Centre of ExcellenceManukau Institute of TechnologyManukauNew Zealand

Personalised recommendations