Search for: All records

Woody plant encroachment (WPE) is transforming grasslands globally, yet accurately mapping this process remains challenging. State-funded, publicly available high-resolution aerial imagery offers a potential solution, including the USDA’s National Agriculture Imagery Program (NAIP) and NSF’s National Ecological Observatory Network (NEON) Aerial Observation Platform (AOP). We evaluated the accuracy of land cover classification using NAIP, NEON, and both sources combined. We compared two machine learning models—support vector machines and random forests—implemented in R using large training and evaluation data sets. Our study site, Konza Prairie Biological Station, is a long-term experiment in which variable fire and grazing have created mosaics of herbaceous plants, shrubs, deciduous trees, and evergreen trees (Juniperus virginiana). All models achieved high overall accuracy (>90%), with NEON slightly outperforming NAIP. NAIP underperformed in detecting evergreen trees (52–78% vs. 83–86% accuracy with NEON). NEON models relied on LiDAR-based canopy height data, whereas NAIP relied on multispectral bands. Combining data from both platforms yielded the best results, with 97.7% overall accuracy. Vegetation indices contributed little to model accuracy, including NDVI (normalized digital vegetation index) and EVI (enhanced vegetation index). Both machine learning methods achieved similar accuracy. Our results demonstrate that free, high-resolution imagery and open-source tools can enable accurate, high-resolution, landscape-scale WPE monitoring. Broader adoption of such approaches could substantially improve the monitoring and management of grassland biodiversity, ecosystem function, ecosystem services, and environmental resilience. 

Abstract In the Central Great Plains of North America, fire suppression is causing transitions from grasslands to shrublands and woodlands. This woody encroachment alters plant community composition, decreases grassland biodiversity, undermines key ecosystem services, and is difficult to reverse. How native grazers affect woody encroachment is largely unknown, especially compared to domesticated grazers. Bison were once the most widespread megafauna in North America and are typically categorized as grazers, with negative effects on grasses that indirectly benefit woody plants. However, bison can negatively impact woody plants through occasional browsing and mechanical disturbance. This study reports on a 30‐year experiment at Konza Prairie Biological Station, a mesic grassland in the Central Great Plains of North America, under fire suppression and experimental presence/absence of bison. Based on remote sensing, deciduous tree canopy cover was lower with bison (6% grazed vs. 16% ungrazed). Shrub land cover showed no difference (42% grazed vs. 41% ungrazed), while herbaceous land cover was higher with bison (51% grazed vs. 40% ungrazed). Evergreen tree canopy cover (Juniperus virginianaL.), which decreases biodiversity and increases wildfire risk, was approximately 0% with bison compared to 4% without bison. In the survival trial ofJ. virginianaseedlings, we found a 40% overwinter mortality with bison, compared to 5% mortality without bison. Compared to ungrazed areas, native plant species richness was 97% and 38% higher in bison‐grazed uplands and lowlands, respectively. Species evenness and Shannon's index were higher in the bison treatment in uplands, but not in lowlands. Bison affected community composition, resulting in higher cover of short grass species and lower tree cover. While grazers are generally assumed to favor woody plants, we found that bison had the opposite effect at low fire frequencies. We argue that the large size of bison and their behaviors account for this pattern, including trampling, horning, and occasional browsing. From a conservation perspective, bison might hamper tree expansion and increase plant diversity in tallgrass prairies and similar grasslands.