Rapid monitoring of the abundance and spread of exotic annual grasses in the western United States using remote sensing and machine learning
Links
- More information: Publisher Index Page (via DOI)
- Data Releases:
- USGS data release - Modelled long-term wildfire occurrence probabilities in sagebrush-dominated ecosystems in the western US (1985 to 2019)
- USGS data release - Historic and future trends in exotic annual grass (%) cover in the western US (1985 to 2019 and 2025 to 2040)
- Open Access Version: Publisher Index Page
- Download citation as: RIS | Dublin Core
Abstract
Exotic annual grasses (EAG) are one of the most damaging agents of change in western North America. Despite known socio-environmental effects of EAG there remains a need to enhance monitoring capabilities for better informing conservation and management practices. Here, we integrate field observations, remote sensing and climate data with machine-learning techniques to estimate and assess patterns of historical (1985–2019; R2 = 0.86 ± 0.05; MAE = 6.7 ± 1.4%), present (2020), and future (2025–2040) EAG abundance (30-m) across much of the western United States. Trend analysis revealed that ∼8% and 1% of the landscape experienced significant rises and declines in historical EAG cover, respectively, with hotspots of invasion generally occurring near roads and along low-to-mid elevation gradients with warmer and drier conditions. Accurate simulations of the response of EAG to changing environmental conditions, disturbances and management treatments indicate that ecosystem resistance to invasion is largely controlled by long-term EAG abundance (surrogate for seed bank), time since and frequency of wildfire, and plant community interactions. Ecological thresholds associated with enhanced probabilities of wildfire occurrence and invasion rates indicate that relatively little (10%) EAG cover is needed to heighten these risks. Climate change is expected to push 8% of the landscape across invasion thresholds by 2040, impacting 6% of existing sage-grouse habitat, and we identify where fuel breaks may be placed to reduce wildfire risks and invasion. Spatially detailed, timely, and accurate depictions of past, present, and future EAG abundance are vital for the protection of life and property and the continued stewardship of sagebrush ecosystems.
Study Area
| Publication type | Article |
|---|---|
| Publication Subtype | Journal Article |
| Title | Rapid monitoring of the abundance and spread of exotic annual grasses in the western United States using remote sensing and machine learning |
| Series title | AGU Advances |
| DOI | 10.1029/2020AV000298 |
| Volume | 2 |
| Issue | 2 |
| Year Published | 2021 |
| Language | English |
| Publisher | American Geophysical Union |
| Contributing office(s) | Earth Resources Observation and Science (EROS) Center |
| Description | e2020AV000298, 22 p. |
| Country | United States |
| State | California, Colorado, Idaho, Nevada, Oregon, Utah, Washington, Wyoming |
| Google Analytic Metrics | Metrics page |