Bayesian habitat suitability mapping for ground-nesting bees using high-resolution remote sensing

Abstract ContextGround-nesting bees are essential pollinators in natural and urban ecosystems, yet their nesting habitats are increasingly threatened by urbanization. Although local ecological drivers of nesting are well understood, applying this knowledge at the landscape scale remains challenging due to limited field data, the spatial scale at which nesting aggregations occur and spatial heterogeneity in urban environments.ObjectivesThis study demonstrates how remote sensing and GIS data can be combined with prior ecological knowledge in a Bayesian framework to model habitat suitability for ground-nesting bees across an urban landscape. We illustrate this approach for the grey-backed mining bee ( Andrena vaga ) in Braunschweig, Germany.MethodsWe derived spatial indicators representing known nesting habitat factors (floral resource proximity, sun exposure, soil texture, vegetation density, probability of tillage, and flood risk) from remote sensing and GIS datasets. A Bayesian logistic regression model integrated these indicators with 55 observed nest locations and literature-based priors to generate habitat suitability and uncertainty maps.ResultsThe resulting model achieved a ROC score of 0.84 and provided spatially explicit estimates of prediction uncertainty. Sparsely vegetated areas with high insolation proved most suitable, yet all environmental variables were important. Bootstrap validation confirmed the robustness of predictions. The model outputs form a decision-support layer for identifying and prioritizing suitable nesting areas in urban planning contexts, incorporating both predicted nesting probability and associated uncertainty.ConclusionsBy integrating ecological knowledge with spatial data, this Bayesian approach enables reliable habitat suitability assessment from limited field observations. The framework may be transferable to other species and urban environments, offering a basis for pollinator-friendly landscape management and conservation planning.