Use of uncrewed aircraft systems (UAS) and regression tree modeling to calculate fractional shrub cover for greater sage-grouse microhabitat

Accurate maps of habitat availability for greater sage-grouse (Centrocercus urophasianus) across broad extents are of paramount importance to conservation efforts in sagebrush ecosystems across the Great Basin, particularly for habitat assessments and mitigation efforts. However, the ability to manage sage-grouse microhabitat is constrained by the spatial and spectral resolution of most remotely sensed vegetation products. Fractional approaches that yield estimates of percent cover at relatively coarse resolution (e.g., 30 ×30 m pixels) are well suited for regional and local estimates at relatively broad spatial scales (e.g., third-order macrohabitat selection and availability). However, precision at individual pixels that could represent finer selection patterns by sage-grouse (e.g., fourth-order microhabitat selection) is often poor. Here, results are presented from a study in central Nevada where previous fractional mapping approaches are advanced by applying regression tree (Cubist) modeling techniques at finer spatial resolutions, with estimates of shrub cover in training plots derived from ultra-high-resolution (< 3 cm) imagery collected with uncrewed aircraft systems (UAS) being applied to multi-spectral WorldView-2 scenes. The approach yields fractional estimates of shrub cover at a 2 m resolution^. Compared to other fractional products, this product more closely correlates with actual field measurements that reflect finer selection patterns of sage-grouse. An advantage of the UAS-regression tree approach is that large volumes of training data can be collected rapidly from UAS compared to traditional ground-based vegetation surveys, which could ultimately yield previously lacking estimates of microhabitat availability across macrohabitat or landscape level extents. Our results provide high-resolution maps of shrub cover with multiple conservation applications, including the development of continuous microhabitat maps to inform sage-grouse habitat restoration efforts and incorporation into planning tools that simulate outcomes of multiple sagebrush management decisions.