Skip to main content
ARS Home » Plains Area » Las Cruces, New Mexico » Range Management Research » Research » Publications at this Location » Publication #424200
Research Project: Knowledge Systems and Tools to Increase the Resilience and Sustainability of Western Rangeland Agriculture

Location: Range Management Research

Title: Sentinel-2 based estimates of rangeland fractional cover and canopy gap class for the western United States

Author
item ALLRED, BRADY - University Of Montana
item McCord, Sarah
item ASSAL, TIMOTHY - Bureau Of Land Management
item Bestelmeyer, Brandon
item Boyd, Chad
item BROOKS, ALEXANDER - Desert Research Institute
item CADY, SAMANTHA - University Of Nebraska
item FUHLENDORF, SAMUEL - Oklahoma State University
item GREEN, SHANE - Natural Resources Conservation Service (NRCS, USDA)
item Harrison, Georgia
item JENSEN, ERIC - Desert Research Institute
item KACHERGIS, EMILY - Bureau Of Land Management
item KNIGHT, ANNA - Us Geological Survey (USGS)
item MATTILIO, CHLOE - University Of Wyoming
item MEALOR, BRIAN - University Of Wyoming
item NAUGLE, DAVID - University Of Montana
item O'LEARY, DYLAN - Oregon State University
item Olsoy, Peter
item Peirce, Erika
item REINHARDT, JASON - Forest Service (FS)
item SHRIVER, ROBERT - University Of Nevada School Of Medicine
item SMITH, JOSEPH - University Of Montana
item TACK, JASON - Us Fish And Wildlife Service
item TANNER, ASHLEY - Texas A&M Agricultural Experiment Station
item TANNER, EVAN - Texas A&M Agricultural Experiment Station
item TWIDWELL, DIRAC - University Of Nebraska
item Webb, Nicholas
item MORFORD, SCOTT - Us Geological Survey (USGS)

Submitted to: Nature
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/22/2025
Publication Date: N/A
Citation: N/A

Interpretive Summary: We explored the use of Sentinel-2 satellites in estimating fractional cover across the United States. We built upon the methods and models in the Rangeland Analysis Platform and constructed a model to estimate the fractional cover of common plant functional types and select genera, and to estimate canopy gap size classes. Using this model, we produced estimates characterizing rangeland vegetation, soil, and canopy gap cover across the western United States for the time period 2018 through 2024.

Technical Abstract: Rangelands are extensive ecosystems, providing important ecosystem services while undergoing continuous change. As a result, there is a need for improved monitoring technologies that better characterize vegetation changes over space and time. Satellite remote sensing has proven effective in this regard, tracking vegetation dynamics at both broad and fine scales. Advancements in technology provide the opportunity to improve monitoring efforts and to better capture subtle yet ecologically significant changes. We leveraged the enhanced spatial, spectral, and temporal resolution of Sentinel-2 satellites to estimate fractional cover and the size distribution of plant inter-canopy gaps across rangelands of the western United States. We developed a one-dimensional convolutional neural network, trained on extensive field data, to predict cover of plant functional types and select genera, and canopy gap size classes. We produced annual, 10 m resolution estimates from 2018 to 2024, providing an unprecedented resource for monitoring rangeland condition and assessing the effectiveness of management strategies.