Loading...
Please wait, while we are loading the content...
Similar Documents
Data from: Mapping beta diversity from space: Sparse Generalized Dissimilarity Modelling (SGDM) for analysing high-dimensional data (Dataset)
| Content Provider | Dryad |
|---|---|
| Author | Leitão, Pedro J. Suess, Stefan Schwieder, Marcel Catry, Inês Milton, Edward Moreira, Francisco Osborne, Patrick E. Pinto, Manuel J. van der Linden, Sebastian Hostert, Patrick Milton, Edward J. |
| Abstract | 1. Spatial patterns of community composition turnover (beta diversity) may be mapped through Generalised Dissimilarity Modelling (GDM). While remote sensing data are adequate to describe these patterns, the often high-dimensional 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. SGDM consists of a two-stage approach, by first transforming the environmental data with a sparse canonical correlation analysis (SCCA), aimed at dealing with high-dimensional datasets, and secondly fitting the transformed data with GDM. The SCCA penalisation parameters are chosen according to a grid search procedure in order to optimise the predictive performance of a GDM fit 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 datasets, including a time series of Landsat data as well as simulated EnMAP hyperspectral data. 3. The proposed approach always outperformed GDM models when fit on high-dimensional datasets. 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 date multispectral 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 datasets 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. |
| File Size | 414454 |
| File Format | HTM / HTML |
| ISSN | 2041210X |
| DOI | 10.5061/dryad.ns7pv |
| Alternate Webpage(s) | https://datadryad.org/stash/downloads/file_stream/28062 |
| Language | English |
| Publisher Date | 2016-03-18 |
| Access Restriction | Open |
| Subject Keyword | Merops Apiaster Luscinia Megarhynchos Galerida Sp. Cuculus Canorus Anthus Campestris Sylvia Cantillans Carduelis Canabinna Sturnus Unicolor Lanius Meridionalis Passer Hispaniolensis Cisticola Juncidis Tetrax Tetrax Upupa Epops Pica Pica Time Series Turdus Merula Falco Naumanni Cyanopica Cookii Gelochelidon Nilotica Clamator Glandarius Ciconia Ciconia Carduelis Carduelis Circus Pygargus Sylvia Melanocephala Sparse Canonical Correlation Analysis Elanus Caeruleus Circus Aeruginosus Hyperspectral Data Melanocorypha Calandra Falco Tinnunculus Lanius Senator Serinus Serinus Bubulcus Ibis Athene Noctua Miliaria Calandra Alectoris Rufa Saxicola Torquata Landsat Generalised Dissimilarity Modelling Sylvia Undata Calandrella Brachydactyla Otis Tarda Columba Palumbus Coturnix Coturnix Picus Viridis Community Modelling Burhinus Oedicnemus Oenanthe Hispanica |
| Content Type | Text |
| Resource Type | Data Set |
| Subject | Ecological Modeling Ecology, Evolution, Behavior and Systematics |
