Wetenschappelijk artikelBetter together? Assessing different remote sensing products for predicting habitat suitability of wetland birds

The increasing availability of remote sensing (RS) products from airborne laser scanning (ALS) surveys, synthetic aperture radar acquisitions and multispectral satellite imagery provides unprecedented opportunities for describing the physical structure and seasonal changes of vegetation. However, the added value of these RS products for predicting species distributions and animal habitats beyond land cover maps remains little explored. Here, we aim to assess how metrics derived from different types of high-resolution (10 m) RS products predict the habitat suitability of wetland birds. We built species distribution models (SDMs) with occurrence observations from territory mapping of two selected wetland bird species (great reed warbler and Savi's warbler) and metrics from a Dutch land cover map, country-wide ALS and Sentinel-1 and Sentinel-2 RS products. We then compared model performance, relative variable importance and response curves of the SDMs to assess the contribution and ecological relevance of each RS product and metric. Our results showed that ALS and Sentinel metrics improve SDMs with only land cover metrics by 11% and 10% of the Area Under Curve (AUC) for the great reed warbler and the Savi's warbler respectively. Assessments of feature importance revealed that all types of RS products contributed substantially to predicting the habitat suitability of these wetland birds, but that the most important variables vary among species. Our study demonstrates that metrics from different high-resolution RS products capture complementary ecological information on animal habitats, including aspects such as the proportional cover of habitat types, vegetation density and the horizontal variability of vegetation height. Land cover maps with detailed spatial and thematic information can already achieve high model accuracies, but adding metrics derived from ALS point clouds and Sentinel imagery further improve model accuracy and enhance the understanding of animal–habitat relationships.