Statistical modelling of habitat selection

• Shaykhah Aldossari ^[1] ; Jason Matthiopoulos ; Dirk Husmeier ^[1]
  1. [1] University of Glasgow

     University of Glasgow

     Reino Unido

     
• Localización: Proceedings of the 35th International Workshop on Statistical Modelling : July 20-24, 2020 Bilbao, Basque Country, Spain / Itziar Irigoien Garbizu (ed. lit.), Dae-Jin Lee (ed. lit.), Joaquín Martínez Minaya (ed. lit.), María Xosé Rodríguez Álvarez (ed. lit.), 2020, ISBN 978-84-1319-267-3, págs. 265-269
• Idioma: inglés
• Enlaces
  • Texto Completo Libro
• Resumen

  • To understand the impact of habitat destruction or modi cation on biodiversity there is increasing demand on predictive models that reliably forecast future changes in species distributions. In the present paper, we build on an existing model, the Generalized Functional Response, whose predictions about habitat preferences and species distribution are robust to changes in habitat availability. We improve upon this model in two distinct ways by using Gaussian mixtures to approximate habitat availability and Gaussian basis functions to describe habitat preferences. The proposed model is found to improve descriptive and predictive performance when applied to realistic simulated data and real species abundance data.