Jensen, E. R. | bioRxiv Science

bioRxiv2025

Estimating rangeland fractional cover and canopy gap size class with Sentinel-2 imagery

Rangelands are extensive ecosystems, providing important ecosystem services while undergoing continuous change. As a result, improved monitoring technologies can help better characterize vegetation change. Satellite remote sensing has proven effective in this regard, tracking vegetation dynamics at broad and fine scales. We leveraged the spatial, spectral, and temporal resolution of Sentinel-2 satellites to estimate fractional cover and canopy gap across rangelands of the western United States. We produced annual, 10 m spatial resolution estimates of fractional cover and canopy gap size class for years 2018 to 2024. Fractional cover estimates include that of common plant functional types (annual forb and grass, bareground, littler, perennial forb and grass, shrub, tree) and select genera (including invasive annual grass species, pinyon-juniper species, and sagebrush species); canopy gap size classes include gap sizes 25 to 50, 51 to 100, 101 to 200, and greater than 200 cm. We make these data available as Cloud Optimized GeoTIFFs, organized as 75x75 km tiles covering the 17 western states of the United States.

ecology↗

bioRxiv2022

Mapping Tree Cover Expansion in Montana, U.S.A. Rangelands using High-Resolution Historical Aerial Imagery

Worldwide, trees are colonizing rangelands with high conservation value. The introduction of trees into grasslands and shrublands causes large-scale changes in ecosystem structure and function, which have cascading impacts to ecosystem services, biodiversity, and agricultural economies. Satellites are increasingly being used to track tree cover at continental to global scales, but these methods can only provide reliable estimates of change over recent decades. Given the slow pace of tree cover expansion, remote sensing techniques that can extend this historical record provide critical insights into the magnitude of environmental change. Here, we estimate conifer expansion in rangelands of the northern Great Plains, United States, North America, using historical aerial imagery from the mid-20th century and modern aerial imagery. We analyzed 19.3 million hectares of rangelands in Montana, USA, using a convolutional neural network (U-Net architecture) and cloud computing to detect tree features and tree cover change. Our bias-corrected results estimate 3.0 {+/-} 0.2 million hectares of conifer tree cover expansion in Montana rangelands, which accounts for 15.4% of the total study area. Overall accuracy was greater than 91%, but producer accuracy was lower than user accuracy (0.60 vs. 0.88). Nonetheless, the omission errors were not spatially correlated, indicating that the method is reliable for estimating the spatial extent of tree cover expansion. Using the model results in conjunction with historical and modern imagery allows for effective communication of the scale of tree expansion while overcoming the recency effect caused by shifting environmental baselines.

ecology↗