Mining citizen science data to predict orevalence of wild bird species

ABSTRACT

The Cornell Laboratory of Ornithology's mission is to interpret and conserve the earth's biological diversity through research, education, and citizen science focused on birds. Over the years, the Lab has accumulated one of the largest and longest-running collections of environmental data sets in existence. The data sets are not only large, but also have many attributes, contain many missing values, and potentially are very noisy. The ecologists are interested in identifying which features have the strongest effect on the distribution and abundance of bird species as well as describing the forms of these relationships. We show how data mining can be successfully applied, enabling the ecologists to discover unanticipated relationships. We compare a variety of methods for measuring attribute importance with respect to the probability of a bird being observed at a feeder and present initial results for the impact of important attributes on bird prevalence.

REFERENCES

• 1: Eric Bauer , Ron Kohavi, An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants, Machine Learning, v.36 n.1-2, p.105-139, July-August 1999 [doi>10.1023/A:1007515423169]
• 2: Leo Breiman, Bagging predictors, Machine Learning, v.24 n.2, p.123-140, Aug. 1996 [doi>10.1023/A:1018054314350]
• 3: L. Breiman. Random forests. Technical Report 567, University of California Berkeley, Statistics Department, 2001.
• 4: W. Buntine. Artificial Intelligence Frontiers in Statistics, chapterLearning Classification Trees. Chapman and Hall, 1993.
• 5: R. Caruana, A. Niculescu, B. Rao, and C. Simms. Evaluating the C -section rate of different physician practices: Using machine learning to model standard practice. In The American Medical Informatics Conference (AMIA), 2003.
• 6: J. Friedman. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5):1189--1232, 2001.
• 7: J. Friedman and B. Popescu. Predictive learning via rule ensembles. Technical report, Stanford University, 2005.
• 8: Isabelle Guyon , André Elisseeff, An introduction to variable and feature selection, The Journal of Machine Learning Research, 3, 3/1/2003
• 9: G. Hooker. Generalized functional ANOVA diagnostics for high dimensionalfunctions of dependent variables. Available at http://ego.psych.mcgill.ca/perpg/pstdc/giles, 2005.
• 10: K. Kira and L. Rendell. The feature selection problem: Traditional methods and a newalgorithm. In Proc. Int. Conf. on Artificial Intelligence (AAAI), 1992.
• 11: R. Kohavi and G. John. The wrapper approach. Artificial Intelligence, 97(1--2), 1997.
• 12: E. L. Lehmann. Nonparametrics: Statistical Methods Based on Ranks. Chapman and Hall/CRC, 1989.
• 13: P. McCullagh and J. A. Nelder. Generalized Linear Models. Mcgraw-Hill, 1989.
• 14: Alexandru Niculescu-Mizil , Rich Caruana, Predicting good probabilities with supervised learning, Proceedings of the 22nd international conference on Machine learning, p.625-632, August 07-11, 2005, Bonn, Germany [doi>10.1145/1102351.1102430]
• 15: Foster Provost , Tom Fawcett, Robust Classification for Imprecise Environments, Machine Learning, v.42 n.3, p.203-231, March 2001 [doi>10.1023/A:1007601015854]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Data mining

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Scientific databases

General Terms:
Experimentation

Keywords:
attribute importance, bagging, decision trees, model inspection, partial dependence function, sensitivity analysis