Community Ecology

, Volume 5, Issue 2, pp 203–225 | Cite as

Sources of uncertainty in ecological modelling: predicting vegetation types from environmental attributes

  • M. B. Dale
  • P. E. R. DaleEmail author


In this paper, we use decision trees to construct models for predicting vegetation types from environmental attributes in a salt marsh. We examine a method for evaluating the worth of a decision tree and look at seven sources of uncertainty in the models produced, namely algorithmic, predictive, model, scenario, objective, context and scale. The accuracy of prediction of types was strongly affected by the scenario and scale, with the most dynamically variable attributes associated with poor prediction, while more static attributes performed better. However, examination of the misclassified samples showed that prediction of processes was much better, with local vegetation type-induced patterns nested within a broader environmental framework.


Salt marsh Vegetation types Decision trees MML Types of uncertainty 



Minimum Message Length.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Adomavicius, G. and A. Tuzhilin. 1997. Discovery of actionable patterns in databases: the action hierarchy approach. In: D. Heckerman, H. Mannila, D. Pregibon and R. Uthurusamy (eds.), Proc. 3rd International Conference on Knowledge Discovery and Data Mining. AAAI. pp. 111–114.Google Scholar
  2. Akaike, H. 1973. Information theory and an extension of the maximum likelihood principle. In: B. Petrov and F. Cáski (eds.) 2nd International Symposium on Information Theory, Akadémiai Kiadó, Budapest, pp. 267–281.Google Scholar
  3. Allwein, E.L., R. E. Schapire and Y. Singer 2000. Reducing multiclass to binary: a unifying approach for margin classifiers. J. Machine Learning Research 1:113–141.Google Scholar
  4. Baxter, J 2000. A model of inductive bias learning. J. Artif. Intell. Res. 12:149–198.CrossRefGoogle Scholar
  5. Beeston, G. R. and M. B. Dale 1975. Multiple predictive analysis: a management tool. Proceedings of the Ecological Society of Australia 9:172–181.Google Scholar
  6. Bengio, Y. and Y. Grandvalet 2003. No unbiased estimator of the variance of k-fold cross-validation. Technical Report 1234, Dept. Inform. Rech. Opérat., Université Montréal.Google Scholar
  7. Boerlijst, M. C. and P. Hogeweg. 1991. Spiral wave structure in prebiotic evolution: hypercycles stable against parasites. Physica D 48:17–28.Google Scholar
  8. Breiman, L., J. H. Friedman, R. A. Orshen and C. J. Stone. 1984. Classification and Regression Trees. Belmont CA. Wadsworth.Google Scholar
  9. Brézillon P. and J-Ch. Pomerol. 1999. Contextual knowledge sharing and cooperation in intelligent assistant systems. Le Travail Humain 62:223–246 PUF, Paris.Google Scholar
  10. Brown, D. E. and C. L. Pittard. 1993. Classification trees with optimal multivariate splits. Proc. International Conf. on Systems, Man and Cybernetics: Systems Engineering in the Service of Humans. I. E. E. E. New York, Vol 3. pp. 475–477.Google Scholar
  11. Carley, K. and M. Palmquist 1992. Extracting, representing and analyzing mental models. Social Forces 70:601–636.CrossRefGoogle Scholar
  12. Chatfield, C. 1995. Model uncertainty, data mining and statistical-inference J. R. Statist. Soc. Series A, 158:419–466.CrossRefGoogle Scholar
  13. Chipman, H., E. I. George and R. E. McCullough 2000. Hierarchical priors for Bayesian CART shrinkage. Statistics and Computing 10:17–24.CrossRefGoogle Scholar
  14. Chipman, H., E. I. George and R. E. McCullough 2001. The practical implementation of Bayesian model selection. IMS Lecture Notes: Monograph Ser. 38:67–136.Google Scholar
  15. Czárán, T., R. F. Hoekstra. and L. Pagie 2002. Chemical warfare between microbes promotes biodiversity. Proc. Natl. Acad. Sci. 99:786–790.CrossRefPubMedPubMedCentralGoogle Scholar
  16. Dale, M. B 1982. Strategy and tactics in pattern analysis: a response to Harrington, Dawes and Ludwig. Austral. J. Ecology 7:411–414.CrossRefGoogle Scholar
  17. Dale, M. B, 1999. The dynamics of diversity: mixed strategy systems Coenoses 13:105–113.Google Scholar
  18. Dale, P. E. R. and M. B. Dale 2002. Optimal classification to describe environmental change: pictures from the exposition. Community Ecology 3:19–29.CrossRefGoogle Scholar
  19. Dale, M. B., P. E. R. Dale and T. Edgoose. 2002a. Using Markov models to incorporate serial dependence in studies of vegetation change. Acta Oecologica 23:261–269.CrossRefGoogle Scholar
  20. Dale, M. B., P. E. R. Dale, C. Li and G. Biswas. 2002b. Assessing impacts of small perturbations using a model-based approach. Ecological Modelling 156:185–199.CrossRefGoogle Scholar
  21. Daley, R., 1977. On the inference of optimal descriptions. Theor. Comput. Sci. 4:301–319.CrossRefGoogle Scholar
  22. De’ath, Glenn, 1999: Principal Curves: A new technique for indirect and direct gradient analysis. Ecology 80:2237–2253.CrossRefGoogle Scholar
  23. Dasarathy, B. V. and A. L. Lakshminarasimhan 1976. Sequential learning employing unfamiliar teacher hypothesis (SLEUTH) with concurrent estimation of both parameters and teacher characteristics. International J. Computer Information Sciences 5:1–7.CrossRefGoogle Scholar
  24. Esposito, F., D. Malerbo and G. Semeraro. 1995. Simplifying decision trees by pruning and grafting: new results. In: N. Larraç and S. Wrobel (eds.), Proc. 8th European Conf. Machine Learning, Lecture Notes in Artificial Intelligence 912 Springer, Berlin, pp. 287–290.Google Scholar
  25. Fisher, D. 1992. Pessimistic and optimistic induction. Technical Report CS-92–12 Dept. Comput. Sci., Vanderbilt Univ.Google Scholar
  26. Fitzgibbon, L. J., D. L. Dowe and L. Allison. 2002. Univariate polynomial inference by Monte Carlo Message Length approximation. In: C. Sammut and A. Hoffman (eds.), Proc. 19th Internatl. Conf. Machine Learning (1CML-2002), Morgan-Kauffman, San Francisco. pp. 147–154.Google Scholar
  27. Forster, M. R 2000. Key concepts in model selection: performance and generalizability. J. Math. Psychol: 44:205–231.CrossRefGoogle Scholar
  28. Freund, Y. and L. Mason. 1999. The alternating decision tree learning algorithm. In: Proc 16th Int. Conf. Machine Learning, Morgan-Kaufman, San Francisco. pp. 124–133.Google Scholar
  29. Friedman, J. H., R. Kohavi and Y. Yun. 1996. Lazy decision trees. in: Proceedings of the 13th National Conference on Artificial Intelligence and Eighth Innovative Applications of Artificial Intelligence Conference, AAAI 96, IAAI 96 AAAI Press / The MIT Press. pp. 717–724.Google Scholar
  30. Fürnkranz, J. 1996. Separate and conquer rule learning. Technical Report TR-96–25. Austrian Research Inst. Artificial Intell., Vienna.Google Scholar
  31. Hájek, P., I. Havel and M. Chytil 1966. The GUHA method of automatic hypotheses determination. Computing 1:293–308.CrossRefGoogle Scholar
  32. Hájek, P. and T. Havránek 1977. On generation of inductive hypotheses. Internatl. J. Man-Mack Stud. 9:415–438.CrossRefGoogle Scholar
  33. Hancock, T, T. Jiang., M. Li and J. Tromp 1996. Lower bounds on learning decision lists and trees. Information and Computation 126:114–122.Google Scholar
  34. Heckman, J 1979. Sample selection bias as a specification error. Econometrika 47:153–161.CrossRefGoogle Scholar
  35. Heitjan, D. F 1993. Ignorability and coarse data: some biomedical examples. Biometrics 49:1099–1109.CrossRefGoogle Scholar
  36. Ho, T. K. 1998. The random subspace method for constructing decision forests. I. E. E. E. Trans. Pattern Analysis Machine Intelligence PAMI-20:832–844.Google Scholar
  37. Hogeweg, P 2002. Computing an organism: on the interface between informatic and dynamic processes. Biosystems 64:97–109.CrossRefPubMedPubMedCentralGoogle Scholar
  38. Hunt, E. B., J. Marin, and P. J. Stone. 1966. Experiments in Induction, Academic Press, New York.Google Scholar
  39. Hyafil, L. and R. L. Rivest 1976. Constructing optimal binary decision trees is NP-complete. Information Processing Letters 5:15–17.CrossRefGoogle Scholar
  40. Jelinski, D. E. and J-G. Wu 1996. The modifiable areal unit problem and implications for landscape ecology. Landscape Ecology 11:129–140.CrossRefGoogle Scholar
  41. Jordan, M., Z. Ghahramani and L. K. Saul. 1997. Hidden Markov decision trees. In: M. C. Mozer, M. I. Jordan and T. Petsche (eds.), Advances in Neural Information Processing Systems 9. MIT Press Cambridge MA.Google Scholar
  42. Lanterman, A. D 2000. Schwarz, Wallace and Rissanen: Intertwining themes in theories of model order estimation. International Statistical Review 69:185–212.CrossRefGoogle Scholar
  43. Li, C. G. Biswas, M. B. Dale and P. E. R. Dale. 2001. Building models of ecological dynamics using HMM based temporal data clustering. In: Advances in Intelligent Data Analysis, the 4th International Conference on Intelligent Data Analysis, Lecture Notes in Computer Science, 2189, Springer-Verlag, Berlin, pp. 53–62.Google Scholar
  44. Loehle, C 1987. Hypothesis testing in ecology: psychological aspects and the importance of theory maturation. Quarterly Review of Biology 62:397–409.CrossRefPubMedPubMedCentralGoogle Scholar
  45. Mac Nally, R 2000. Regression and model-building in conservation biology, biogeography and ecology: The distinction between - and reconciliation of - ‘predictive’ and ‘explanatory’ models. Biodiversity and Conservation 9:655–671.CrossRefGoogle Scholar
  46. Macnaughton-Smith, P 1963. The classification of individuals by the possession of attributes associated with a criterion. Biometrics 19:364–366.CrossRefGoogle Scholar
  47. Macnaughton-Smith, P. 1965. Some statistical and other numerical methods for classifying individuals. Home Office Research Unit Report 6, Home Office, London.Google Scholar
  48. Mehta, M., J. Rissanen and R. Agrawal. 1995. MDL-Based Decision Tree Pruning. Proc. 1st International Conf. Knowledge Discovery and Data Mining (KDD’95), pp. 216–221.Google Scholar
  49. Mingers, J 1989. An empirical comparison of selection measures for decision tree induction. Machine Learning 3:319–342.Google Scholar
  50. Mikkelson, G. M 2001. Complexity and verisimilitude: realism in ecology. Biology and Philosophy 16:533–546.CrossRefGoogle Scholar
  51. Murphy, P. M. and M. J. Pazzani. 1991. ID2-of-3: Constructive induction of M-of-N concepts for discriminators in decision trees. Proc. 8th International workshop Machine Learning, Morgan Kaufmann, San Mateo, CA. pp. 183–187.Google Scholar
  52. Murthy, S., S. Kasif and S. Salzberg 1994. A system for induction of oblique decision trees. J. Artif. Intell. Res. 2:1–32.CrossRefGoogle Scholar
  53. Oates, T. and D. Jensen. 1999. Toward a Theoretical Understanding of Why and When Decision Tree Pruning Algorithms Fail. Proc. 16th National Conf. Artificial Intelligence and 11th Conf. Innovative Applications of Artificial Intelligence, AAAI Press / The MIT Press. pp. 372–378.Google Scholar
  54. Oliver, J. and Baxter, R. 1994. MML and Bayesianism: similarities and differences. Technical Report 206, Department of Computer Science, Monash University.Google Scholar
  55. Oliver, J. and Hand, D 1996. Averaging over decision trees. J. Classif. 13:281–297.CrossRefGoogle Scholar
  56. O’Neill, R. V., D. L. DeAngelis, J. B. Waide and T. F. H. Allen, 1986. A Hierarchical Concept of Ecosystems, Princeton Univ. Press, Princeton, N.J.Google Scholar
  57. Opitz, D. and R. Machin 1999. Popular ensemble methods: an empirical study. J. Artif. Intell. Res. 11:160–198.CrossRefGoogle Scholar
  58. Picard, R. R. and K. N. Berk 1990. Data Splitting. American Statistician 44:140–147.Google Scholar
  59. Posse, C. 1995a. Tools for two-dimensional exploratory projection pursuit. J. Computer Graphics Statist. 4:83–100.Google Scholar
  60. Posse, C. 1995b. Projection pursuit exploratory data analysis. Computat. Statist. Data Anal. 20:669–687.CrossRefGoogle Scholar
  61. Quinlan, J. R. 1993. C4.5: Programs for Machine Learning, Morgan Kaufmann: San Mateo, CA.Google Scholar
  62. Ramsey, J. B. and H-J. Yuan 1990. The statistical properties of dimension calculations. Nonlinearity 3:155–176.CrossRefGoogle Scholar
  63. Rastetter, E. B., A. W. King, B. J. Cosby, G. M. Hornberger, R. V. O’Neill and J. E. Hobbie 1992. Aggregating fine-scale ecological knowledge to model coarser-scale attributes of ecosystems. Ecological Applications 2:55–70.CrossRefGoogle Scholar
  64. Riddle, B. R. and D. J. Hafner 1999. Species as units of analysis in ecology and biogeography: time to take the blinkers off. Global Ecol. Biogeog. 8:433–441.CrossRefGoogle Scholar
  65. Robnik-Sikonja, M. and I. Kononenko. 1998. Pruning Regression Trees with MDL. In: Henri Prade (Ed.): Proc. 13th European Conf. Artificial Intelligence, Brighton, UK, August 23–28 1998. John Wiley and Sons, Chichester. pp. 455–459.Google Scholar
  66. Rymon, R. 1993. An SE-tree based characterization of the induction problem. Proceedings of the 10th International Conference on Machine Learning, ML-93, Morgan Kaufmann, CA, pp. 268–275.Google Scholar
  67. Schwarz, G 1978. Estimating dimension of a model. Ann. Statist. 6:461–464.CrossRefGoogle Scholar
  68. Srikant, R. and R. Agrawal. 1995. Mining generalized association rules. Res. Rep. RJ9963, IBM Almaden Res. Cent. San José, CA. and Proc. 21st Very Large Data Base Conference, Zurich, 13 pp.Google Scholar
  69. Stone, M. 1977. An Asymptotic Equivalence of Choice of Model by Cross-Validation and Akaike’s Criterion. J. R. Stat. Soc., B 38:44–47.Google Scholar
  70. Tan, P. J. and D. L. Dowe. 2002. MML inference of decision graphs with multi-way joins. Lecture Notes in Artificial Intelligence 2557, pp. 131–142.Google Scholar
  71. Tan, P. J. and D. L. Dowe. 2003. MML inference of decision graphs with multi-way joins and dynamic attributes. Proc. 16th Australian Joint Conference on Artificial Intelligence, Perth, Dec. (to appear).CrossRefGoogle Scholar
  72. Ting, K. M. 1994. The problem of small disjuncts: its remedy in decision trees. Proc 10th Canadian Conf. Artif. Intell. pp. 91–97.Google Scholar
  73. Todorovski, L. and S. Dzeroski. 2000. Combining multiple models with meta decision trees. Principles of Data Mining and Knowledge Discovery, pp. 54–64.Google Scholar
  74. Tothill, J. C., J. N. G. Hargreaves and R. M. Jones. 1978. - BOTANAL - a comprehensive sampling and computing procedure for estimating pasture yield and composition. I. Field sampling. Technical Memorandum 8, CSIRO, Division Tropical Crops Pastures, Brisbane.Google Scholar
  75. Utgoff, P. E. 1994. An improved algorithm for incremental induction of decision trees. In: W. Cohen and H. Hirsh (eds.), Proceedings of the 11th International Conference on Machine Learning, New Brunswick, NJ. Morgan Kaufmann. pp. 318–325.Google Scholar
  76. van den Bosch, A., A. Weijters, H. J. Van der Herik. and W. Daelemans. 1997. When small disjuncts abound, try lazy learning: a case study. Proc. 7th Belgian-Dutch Conf. Machine Learning, pp. 109–118.Google Scholar
  77. van de Velde, W. 1990. Incremental induction of topologically minimal decision trees. In: Proceedings of the 7th International Conference on Machine Learning, Austin, TX. Morgan Kaufmann. pp. 66–74.Google Scholar
  78. Vapnik V.N. 1995. The Nature of Statistical Learning Theory. Springer, Berlin.CrossRefGoogle Scholar
  79. Wallace, C. S. 1996. MML inference of predictive trees, graphs and nets. In: A. Gammerman (ed.), Computational Learning and Probabilistic Reasoning, John Wiley. pp. 43–66.Google Scholar
  80. Wallace, C. S. and D. L. Dowe 1999. Minimum Message Length and Kolmogorov complexity. Comput. J. 42:270–283.CrossRefGoogle Scholar
  81. Wallace, C. S. and J. Patrick 1993. Coding decision trees. Machine Learning 11:7–22.CrossRefGoogle Scholar
  82. Webb, G. I. 1994. Generality is more significant than complexity: toward alternatives to Occam’s razor. In: C. Zhang, J. Debenham and D. Lukose (eds), AI’94 - Proc. 7th Australian Joint Conf. Artificial Intelligence, Armidale, World Scientific. pp. 60–67.Google Scholar
  83. Widmer, G. and M. Kubat 1996. Learning in the presence of concept drift and hidden contexts. Machine Learning 23:69–101.Google Scholar
  84. Williams, G. J. 1988 Combining decision trees. In: J. S. Gero and R. Stanton (eds.), Artifiical Intelligence: Developments and Applications. Elsevier Scientific, Amsterdam. pp. 273–289.Google Scholar
  85. Wittgenstein, L. 1995. Tractacus 5:3651Google Scholar
  86. Yamada, H. and S. Amaroso 1971. Structural and behavioural equivalences of tessellation automata. Information and Control 18:1–31.CrossRefGoogle Scholar
  87. Young, P., S. Parkinson and M. Lees 1996. Simplicity out of complexity in environmental modeling: Occam’s razor revisited. J. Appl. Statist. 234:165–210.CrossRefGoogle Scholar
  88. Zhang, J., Y-S. Yim and J. Yang 1997. Intelligent selection of instances for prediction function in lazy learning algorithms. Artif. Intel. Rev. 11:175–192.CrossRefGoogle Scholar

Copyright information

© Akadémiai Kiadó, Budapest 2004

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (, which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Authors and Affiliations

  1. 1.Australian School of Environmental StudiesGriffith UniversityNathanAustralia

Personalised recommendations