Description Details Author(s) References See Also
The present focus is on ensemble boosted regression tree methods such as those used in Bhatt et al. (2013). This will be developed to incorporate other statistical models, methods for selection of pseudo-absence data and other modelling choices.
Package: | seegSDM |
Type: | Package |
Version: | 0.1-9 |
Date: | 2016-03-14 |
License: | GPL(>=2) |
Functions are provided to assist with the seeg SDM workflow:
quality control of occurrence and covariate data
generation of pseudo-absence data
fitting ensembles of models in parallel
combining model ensembles to produce final predictions, uncertainty estimates and model summaries
Nick Golding, with some functions based on code by Samir Bhatt
Bhatt et al. (2013) The global distribution and burden of dengue. Nature http://www.nature.com/nature/journal/v496/n7446/full/nature12060.html
Functions for quality control:
Functions for manipulating rasters and shapefiles:
biasGrid
, featureDensity
, gaussWindow
, osgb36
, wgs84
, en2os
, extent2poly
, importRasters
, maxExtent
, percCover
, buildSP
, nearestLand
, extractAdmin
,
getGAUL
, occurrence2SPDF
Functions for generating pseudo-absences:
Functions for running and assessing BRT ensembles:
runBRT
, getEffectPlots
, getRelInf
, combinePreds
Miscellaneous functions:
rmse
, sdWeighted
, splitIdx
, subsample
Synthetic data for testing and examples:
occurrence
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.