Clustering future scenarios based on predicted range maps

Abstract

Predictions of biodiversity trajectories under climate change are crucial in order to act effectively in maintaining the diversity of species. We propose an interpretable and flexible two-step methodology to measure the similarity between predicted species range maps and to cluster the future scenario predictions utilizing a spectral clustering technique. Clustering based on predicted species range maps is mainly driven by the amount of warming rather than climate model or future scenario.

Publication
Methods in Ecology and Evolution, (14), pp. 1346–1360, https://doi.org/10.1111/2041-210X.14080