Natural history museums and herbaria collectively hold hundreds of millions of zoological, botanical, and paleontological specimens. These collections serve as the foundation for understanding the distribution of life on Earth and the basis for addressing loss of biodiversity, emerging diseases, and other pressing global problems as well as important question in ecology and evolution. One of the short comings of these kind of data is that the lack of evidence of the presence of a species in a certain region does not mean the species is truly absent there. Likewise, specimens are often misidentified, and therefore the report of a species in a locality is not always evidence that a viable population occurs there. The goal of this project is to develop a method which could be used to estimate the probability of presence of a species in a certain study region based on certain sampling effort and presence reports.

bdvis

Biodiversity data Visualizations in R

betapart_fork

bigspatialdatar

Slides and lecture notes on how to process large spatial data with R

biocoll2021

Notes for the tutorial "Introduction to Machine Learning with R" given at "Biometrisches Kolloquium 2021"

biodiversityobservationsminer

A web application to unlock primary biodiversity data from published literature

biomapme

Functions for generating gridded biodiversity maps from point (incidence) data

bioregion

bioregionalisation

Notes I've made on bioregionalisation

bioregionalization

R package to run several clustering methods

bioregions

Infomap Bioregions: Interactive mapping of biogeographical regions from species distributions

birdseye

Tools for geographic analysis

blockcv

The blockCV package creates spatially or environmentally separated training and testing folds for cross-validation to provide a robust error estimation in spatially structured environments.