CoChat
Sign Up
Cited by 5,890

The DOI matches its Crossref record, with a small difference in title or year; 4 of the 4 references it cites were found in a registry or an index.

Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation

Phillips, Steven J., Dudík, Miroslav·2008·Ecography
DOI 10.1111/j.0906-7590.2008.5203.x
Open this paper in CoChat — free account

Abstract

Accurate modeling of geographic distributions of species is crucial to various applications in ecology and conservation. The best performing techniques often require some parameter tuning, which may be prohibitively time‐consuming to do separately for each species, or unreliable for small or biased datasets. Additionally, even with the abundance of good quality data, users interested in the application of species models need not have the statistical knowledge required for detailed tuning. In such cases, it is desirable to use “default settings”, tuned and validated on diverse datasets. Maxent is a recently introduced modeling technique, achieving high predictive accuracy and enjoying several additional attractive properties. The performance of Maxent is influenced by a moderate number of parameters. The first contribution of this paper is the empirical tuning of these parameters. Since many datasets lack information about species absence, we present a tuning method that uses presence‐only data. We evaluate our method on independently collected high‐quality presence‐absence data. In addition to tuning, we introduce several concepts that improve the predictive accuracy and running time of Maxent. We introduce “hinge features” that model more complex relationships in the training data; we describe a new logistic output format that gives an estimate of probability of presence; finally we explore “background sampling” strategies that cope with sample selection bias and decrease model‐building time. Our evaluation, based on a diverse dataset of 226 species from 6 regions, shows: 1) default settings tuned on presence‐only data achieve performance which is almost as good as if they had been tuned on the evaluation data itself; 2) hinge features substantially improve model performance; 3) logistic output improves model calibration, so that large differences in output values correspond better to large differences in suitability; 4) “target‐group” background sampling can give much better predictive performance than random background sampling; 5) random background sampling results in a dramatic decrease in running time, with no decrease in model performance.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1111/j.0906-7590.2008.5203.x

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • MAXENT commonly outperformed other modelling techniques that use presence-only or presence-absence data, especially when dealing with small sample sizes or non-random sampling.

    “MAXENT v. 3.3.3 (http://www.cs.princeton.edu/~schapire/ maxent/) was used to model terra preta distributions, as it commonly outperformed other modelling techniques that use presence-only or presence-absence data, especially when dealing with small sample sizes or non-random sampling [47-49].”

    From Predicting pre-columbian anthropogenic soils in amazonia (2014) · cites this paper as [47]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 35

  1. 10.1046/j.1365-2699.2003.00867.x · DOI
  2. 10.1111/j.1365-2486.2005.01000.x · DOI
  3. Dudík M., 2004, Proceedings of the Seventeenth Annual Conference on Computational Learning Theory, 655
  4. Dudík M., 2005, Advances in Neural Information Processing Systems 18, 323
  5. Elith J., 2002, Quantitative methods for conservation biology, 39
  6. 10.1111/j.1472-4642.2007.00340.x · DOI
  7. 10.1111/j.2006.0906-7590.04596.x · DOI · Paper page
  8. 10.1017/S0376892997000088 · DOI · Paper page
  9. 10.1214/aos/1176347963 · DOI
  10. 10.1016/j.tree.2004.07.006 · DOI
  11. 10.1073/pnas.0505754103 · DOI
  12. Grünwald P., 2000, Proceedings of the Sixteenth Annual Conference on Uncertainty in Artificial Intelligence (UAI2000), 238
  13. 10.1214/009053604000000553 · DOI
  14. Hastie T., 1990, Generalized additive models
  15. 10.1007/978-0-387-21606-5 · DOI · Paper page
  16. 10.2193/0022-541X(2004)068[0774:UAIOLR]2.0.CO;2 · DOI
  17. Ng A. Y., 2001, On discriminative vs. generative classifiers: a comparison of logistic regression and naive Bayes, Adv. Neural Inform. Process. Syst., 14, 605
  18. 10.1111/j.1365-2699.2006.01460.x · DOI
  19. 10.17161/bi.v3i0.29 · DOI
  20. 10.1126/science.285.5431.1265 · DOI
  21. 10.1614/P2002-081 · DOI
  22. Phillips S. J., 2004, Proceedings of the Twenty‐First International Conference on Machine Learning, 472
  23. Phillips S. J., 2005, Maxent software for species distribution modeling
  24. 10.1016/j.ecolmodel.2005.03.026 · DOI · Paper page
  25. 10.1046/j.1523-1739.2001.015003648.x · DOI
  26. 10.1111/j.1365-2699.2006.01466.x · DOI
  27. 10.1046/j.1365-2699.2003.00946.x · DOI
  28. 10.1038/nature02121 · DOI
  29. 10.1111/j.1365-2486.2005.001018.x · DOI
  30. Tibshirani R., 1996, Bias, variance and prediction error for classification rules
  31. Topsøe F., 1979, Information theoretical optimization techniques, Kybernetika, 15, 8
  32. Ward G., 2007, Presence‐only data and the em algorithm
  33. 10.1162/neco.1995.7.1.117 · DOI · Paper page
  34. 10.1016/S0304-3800(02)00199-0 · DOI
  35. 10.1002/1097-0258(20000715)19:13<1771::AID-SIM485>3.0.CO;2-P · DOI

Cited by

Sorted by citations

Metadata

Authors
Phillips, S. J., & Dudík, M.
Venue
Ecography
Publisher
Wiley
Published
2008-03-28
Volume
31
Issue
2
Pages
161-175
ISSN
  • 0906-7590
  • 1600-0587
DOI
10.1111/j.0906-7590.2008.5203.x
Cited by
5,890
References
4
Language
en
Licence
onlinelibrary.wiley.com/termsAndConditions#vor (vor)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review