# Using graph theory to define data-driven ecoregion and bioregion maps

*2025-04-01 — idea*


Maps of biologically driven regionalization (e.g. ecoregions and bioregions)
are useful in conservation science and policy as they help identify areas with
similar ecological characteristics, allowing for more targeted, efficient, and
ecosystem-specific management strategies. These regions provide a framework for
prioritizing conservation efforts, monitoring biodiversity, and aligning
policies across political boundaries based on ecological realities rather than
arbitrary lines. However these products have historically been "hand drawn" by
experts and are mostly based on plant distribution data only.


Graph theory offers numerous tools to analyse and highlight the relation
between data points and has been used to study spatially explicit datasets.
However, these tools have never been applied to global-scale systematic species
distribution datasets. The [Key Biodiversity Areas](https://www.keybiodiversityareas.org/) (KBA) Secretariat has
compiled such a comprehensive dataset that includes Range and Area Of Habitat
(AOH) information for all species currently mapped on the [IUCN Red List](https://www.iucnredlist.org/) (92,255
species; each species modelled for both its breeding and non-breeding
distribution), along ~85 million hexagonal 6 km2 cells that cover the entire
globe. The entire dataset is comprised of 32 billion spatially explicit data
records.

## The summer project

We aim to use clustering analysis for community detection on a combination of species
co-occurrence and cell proximity, to create a data-driven spatial
regionalization of the world based on all spatially described species. The
project will involve compiling all this data into a graph database, identifying
suitable clustering approaches for community detection, and analysing results
to identify informative clustering thresholds.

This is a good summer project for a computer science student who wants to
get more familiar with graph databases, data science and environmental/biodiversity
approaches.
Status: Available
Level: Any
Year: 2025
Project: Mapping LIFE on Earth
Supervisors: Anil Madhavapeddy, Daniele Baisero, Michael Dales

---
Canonical: https://anil.recoil.org/ideas/ecoregion-maps
Type: idea
License: CC BY 4.0 <https://creativecommons.org/licenses/by/4.0/>
Tags: conservation, biodiversity, spatial, :life, urop
