Guido A. Moreira
CBMA, Centro de Biologia Molecular e Ambiental
Abstract: Species distribution models (SDMs) are extremely useful for determining preferences and habitats for different species. Appropriate estimation of species distributions depends on the adequate random sampling scheme which is not always available. Instead, data is frequently composed of georeferenced locations where the species has been observed, which is commonly referred to as presence-only (PO) data. This proposal uses an Inhomogeneous Poisson Process without the need to approximate the intractable integral in its likelihood function and deals with a parameter and model identifiability issue. Results are provided on two real data sets containing Eucalyptus and Angico tree presences, and the model is compared with currently used traditional solutions.