Faculty of Mathematics and Natural Sciences - Earth Observation Lab

Faculty of Mathematics and Natural Sciences | Geography Department | Earth Observation Lab | News | Archive | Paper on mapping beta-diversity from space by Pedro J. Leitão et.al. just published online...

Paper on mapping beta-diversity from space by Pedro J. Leitão et.al. just published online...

in Methods in Ecology and Evolution (Early View): The publishers used Sparse Generalised Dissimilarity Modelling (SGDM) for analysing high-dimensional data to map beta divesity from space.

enjoy reading the paper

 

Summary (from the paper)


1. Spatial patterns of community composition turnover (beta diversity) may bemapped through generalised dissimilarity
modelling (GDM).While remote sensing data are adequate to describe these patterns, the often highdimensional
nature of these data poses some analytical challenges, potentially resulting in loss of generality. This
may hinder the use of such data for mapping and monitoring beta-diversity patterns.
2. This study presents Sparse Generalised Dissimilarity Modelling (SGDM), a methodological framework
designed to improve the use of high-dimensional data to predict community turnover with GDM. SGDMconsists
of a two-stage approach, by first transforming the environmental data with a sparse canonical correlation
analysis (SCCA), aimed at dealing with high-dimensional data sets, and secondly fitting the transformed data
with GDM. The SCCApenalisation parameters are chosen according to a grid search procedure in order to optimise
the predictive performance of aGDMfit on the resulting components. The proposed method was illustrated
on a case study with a clear environmental gradient of shrub encroachment following cropland abandonment,
and subsequent turnover in the bird communities. Bird community data, collected on 115 plots located along the
described gradient, were used to fit composition dissimilarity as a function of several remote sensing data sets,
including a time series of Landsat data as well as simulated EnMAP hyperspectral data.
3. The proposed approach always outperformedGDMmodels when fit on high-dimensional data sets. Its usage
on low-dimensional data was not consistently advantageous.Models using high-dimensional data, on the other
hand, always outperformed those using low-dimensional data, such as single-datemultispectral imagery.
4. This approach improved the direct use of high-dimensional remote sensing data, such as time-series or hyperspectral
imagery, for community dissimilarity modelling, resulting in better performing models. The good
performance of models using high-dimensional data sets further highlights the relevance of dense time series
and data coming from new and forthcoming satellite sensors for ecological applications such as mapping species
beta diversity.