Sensitivity of predictive species distribution models to change in grain size

TLDR

Predictive species distribution modelling (SDM) is essential for biodiversity conservation, yet the resolution of environmental layers may influence predictions. The study tests whether a ten‑fold coarsening of resolution affects SDM predictive performance and whether such effects depend on region, modelling technique, or species. Ten distinct presence‑only modelling techniques were applied to 50 species across five regions to evaluate performance under two resolutions. A ten‑fold change in grain size generally degrades model performance, but improvements can occur; effects vary by region, technique, and species, with tree species in high‑accuracy regions most affected, while boosted regression trees remain best at both resolutions, and larger training samples yield more sensitive models.

Abstract

ABSTRACT Predictive species distribution modelling (SDM) has become an essential tool in biodiversity conservation and management. The choice of grain size (resolution) of environmental layers used in modelling is one important factor that may affect predictions. We applied 10 distinct modelling techniques to presence‐only data for 50 species in five different regions, to test whether: (1) a 10‐fold coarsening of resolution affects predictive performance of SDMs, and (2) any observed effects are dependent on the type of region, modelling technique, or species considered. Results show that a 10 times change in grain size does not severely affect predictions from species distribution models. The overall trend is towards degradation of model performance, but improvement can also be observed. Changing grain size does not equally affect models across regions, techniques, and species types. The strongest effect is on regions and species types, with tree species in the data sets (regions) with highest locational accuracy being most affected. Changing grain size had little influence on the ranking of techniques: boosted regression trees remain best at both resolutions. The number of occurrences used for model training had an important effect, with larger sample sizes resulting in better models, which tended to be more sensitive to grain. Effect of grain change was only noticeable for models reaching sufficient performance and/or with initial data that have an intrinsic error smaller than the coarser grain size.