Data availability impacts the predictive accuracy of pressure-based biodiversity models

Jakob Nyström, Jeffrey R. Smith, Lisa Mandle, Andrew Gonzalez , Thomas B. Schön, Tobias Andermann

Amidst the biodiversity crisis, there is high demand for spatially explicit biodiversity indicators. Global models that quantify impacts of human pressures provide important insights for conservation, but their accuracy in spatial projections has yet to be systematically tested. Here we evaluate this using a global dataset of 25,987 species inventories from 681 studies. We find that mixed models with study attributes as random effects - common in meta-analysis and used in several indicators - exhibit low predictive accuracy. This is driven by reliance on a small set of averaged fixed effects. In contrast, a biogeographic-taxonomic model structure with explicit environmental covariates shows relatively higher interpolation accuracy. However, accuracy when extrapolating to other contexts remains low, due to distribution shifts in environmental conditions. These patterns apply to site-level diversity and differences between sites. Both models estimate similar land-use impacts, in line with previous research, yet our results highlight the challenging gap between effect size inference and prediction. Models are essential for informed conservation efforts, but their applicability is fundamentally constrained by data availability. Whereas countries with extensive data can build high-fidelity national indicators, accelerated data collection and model development are needed to better support data-poor regions with localized and actionable insights.