A maximum entropy approach to species distribution modeling

Publication Type:

Conference Paper

Authors:

Phillips, Steven J.; Dudík, Miroslav; Schapire, Robert E.

Source:

21st International Conference on Machine Learning, Banff, Alberta, Canada (2004)

ISBN:

1-58113-838-5

Call Number:

U04PHI01IDUS

URL:

http://dl.acm.org/citation.cfm?id=1015330

Keywords:

distribution modeling, maxent, maximum entropy, species distribution

Abstract:

The authors study the problem of modeling species’ geographic distributions, a critical problem in conservation biology. They propose the use of maximum-entropy techniques for this problem, specifically, sequential-update algorithms that can handle a very large number of features. They describe experiments comparing maxent with a standard distribution-modeling tool, called GARP, on a dataset containing observation data for North American breeding birds. They also study how well maxent performs as a function of the number of training examples and training time, analyze the use of regularization to avoid overfitting when the number of examples is small, and explore the interpretability of models constructed using maxent.

Notes:

ELECTRONIC FILE - Zoology

Book title: Proceedings of the Twenty-First International Conference on Machine Learning