Species mapping revolutionized

Prediction of species' distributions is central to diverse applications in ecology, evolution and conservation science. There is now increasing electronic access to vast sets of occurrence records in museums and herbaria all over the world, yet there has been little effective guidance on how best to use this information to model and predict species distributions. A recent study in the journal Ecography by an international team of researchers now offers the by far most comprehensive model comparison ever made, comparing the performance of 16 methods over 226 species from 6 regions of the world. The study then takes the approach one step further and validates model-based predictions against data collected independently. Along with well-established modelling methods, the team have explored novel approaches such as machine-learning methods and community models, both of which have features that may make them particularly well suited to noisy or sparse information that are typical of species' occurrence data. The novel methods consistently outperformed more established methods. The results of the study hold great promise for the use of data from the World's museums and herbaria and will be invaluable for anyone wanting to analyse species' distributions in years to come.

To read the full article visit http://www.blackwell-synergy.com/doi/abs/10.1111/j.2006.0906-7590.04596.x

---

---