Author(s): Steven J Phillips, Anderson RP, Schapire RE
We study the problem of modeling species geographic distributions, a critical problem in conservation biology. We propose the use of maximum-entropy techniques for this prob- lem, specifically, sequential-update algorithms that can handle a very large number of fea- tures. We describe experiments comparing max- ent with a standard distribution-modeling tool, called GARP, on a dataset containing observation data for North American breeding birds. We also study how well maxent performs as a function of the number of training examples and train- ing time, analyze the use of regularization to avoid overfitting when the number of examples is small, and explore the interpretability of mod- els constructed using maxent.