Transferability and model evaluation in ecological niche modeling: a comparison of GARP and Maxent
Tóm tắt
We compared predictive success in two common algorithms for modeling species’ ecological niches, GARP and Maxent, in a situation that challenged the algorithms to be general – that is, to be able to predict the species’ distributions in broad unsampled regions, here termed transferability. The results were strikingly different between the two algorithms – Maxent models reconstructed the overall distributions of the species at low thresholds, but higher predictive levels of Maxent predictions reflected overfitting to the input data; GARP models, on the other hand, succeeded in anticipating most of the species’ distributional potential, at the cost of increased (apparent, at least) commission error. Receiver operating characteristic (ROC) tests were weak in discerning models able to predict into broad unsampled areas from those that were not. Such transferability is clearly a novel challenge for modeling algorithms, and requires different qualities than does predicting within densely sampled landscapes – in this case, Maxent was transferable only at very low thresholds, and biases and gaps in input data may frequently affect results based on higher Maxent thresholds, requiring careful interpretation of model results.
Từ khóa
Tài liệu tham khảo
Anon, 2001, HYDRO1k Elevation Derivative Database
Elith J., 2002, Predicting species occurrences: issues of scale and accuracy, 303
Eng J., 2005, ROC analysis: web‐based calculator for ROC curves
Guisan A., 2007, What matters for predicting spatial distributions of trees: techniques, data, or species’ characteristics?
Hijmans R. J., 2005, WorldClim, ver. 1.3
Pereira R. S., 2002, Desktop GARP
Phillips S. J., 2006, Maxent software for species habitat modeling, ver. .2.0, 2
Phillips S. J., 2004, Proc. 21st Int. Conf. on Machine Learning, 655
Sauer J. R., 2001, The North American Breeding Bird Survey, results and analysis 1966–2000, ver. 2001.2
Schröder B., 1999, Are habitat models transferable in space and time?, Zeitschr. Ökol. Natursch., 8, 195
Stockwell D. R. B., 2002, Predicting species occurrences: issues of scale and accuracy, 537