370 Leveraging remote sensing products to estimate forage productivity in the Canadian Prairies

Abstract Remote sensing is widely used for land cover classification applications. This technology supports the development of land management practices and policies to achieve conservation and economic goals in agricultural landscapes. In animal production, remote sensing aids in reducing grassland degradation and enhancing livestock and crop production. The objective of this work is to discuss recent satellite- and drone-based remote sensing applications for grassland mapping in the Canadian Prairies. Using a satellite-based approach, the agreement between remotely sensed land cover maps and non-spatial government records was assessed for public agricultural Crown lands in southern Manitoba. Two different land cover classification products derived from satellite imagery [i.e., the Manitoba Grassland Inventory (MGI) prepared by the Province of Manitoba and the Annual Crop Inventory (ACI) prepared by Agriculture and Agri-Food Canada] were merged into a single mosaic covering the entire Agro-Manitoba region. Non-spatial official records were georeferenced and summarized through parcel delineation using geographic information system (GIS) and R programming tools. Comparison of the two datasets revealed low agreement between related grassland classes (i.e., forests and shrublands; and native and tame grasslands) due to spectral similarities. However, grouping these related vegetation types into broader categories (i.e., forests and shrublands as woody vegetation; native and tame grasslands as grassy vegetation) significantly improved overall agreement, with a difference of less than 3% observed between remotely sensed datasets and official records. The derived grassland classification was then used to assess the grazing status of the agricultural Crown lands by estimating stocking rates in animal unit months (AUM) and utilizing historical yield data available from three separate field surveys conducted between 2004 and 2020 across the region. Average carrying capacities ranged from 0.71 AUM/ha to 1.99 AUM/ha. Overall, the analysis using remotely sensed data indicated that the forage resources in the Crown lands were underutilized by 45%. To further explore the potential of using high-resolution remote sensing to map grasslands, ongoing research involves the use of a drone-mounted hyperspectral sensor (HySpex Mjolnir VS-620) covering a spectral range from 400 to 2,500 nm across 490 spectral channels. This sensor enables grassland mapping at significantly greater spatial and spectral resolutions. Monthly surveys during the snow-free period will be conducted in 12 study sites across the Agro-Manitoba region in 2024 and 2025, with biomass samples collected to model grassland distribution and productivity. The outcomes of this study will offer critical insights into leveraging specific wavelengths for grassland mapping and strategies for extrapolating these insights to larger geographical areas using satellite imagery. Overall, the efforts described above underscore the significance of remote sensing approaches in managing agricultural landscapes and provide valuable insights for land managers, policymakers, and stakeholders to promote sustainable agricultural production in grasslands.