Research Database
Displaying 1 - 3 of 3
Disentangling drivers of annual grass invasion: Abiotic susceptibility vs. fire-induced conversion to cheatgrass dominance in the sagebrush biome
Year: 2024
Invasive annual grasses are often facilitated by fire, yet they can become ecologically dominant in susceptible locations even in the absence of fire. We used an extensive vegetation plot database to model susceptibility to the invasive annual grass cheatgrass (Bromus tectorum L.) in the sagebrush biome as a function of climate and soil water availability variables. We built random forest models predicting cheatgrass presence or dominance (>15 % relative cover) under unburned (37,219 plots) and burned conditions (6340 plots). We mapped predicted probability of cheatgrass…
Publication Type: Journal Article
Global rise in forest fire emissions linked to climate change in the extratropics
Year: 2024
Climate change increases fire-favorable weather in forests, but fire trends are also affected by multiple other controlling factors that are difficult to untangle. We use machine learning to systematically group forest ecoregions into 12 global forest pyromes, with each showing distinct sensitivities to climatic, human, and vegetation controls. This delineation revealed that rapidly increasing forest fire emissions in extratropical pyromes, linked to climate change, offset declining emissions in tropical pyromes during 2001 to 2023. Annual emissions tripled in one extratropical pyrome due to…
Publication Type: Journal Article
Predicting daily firefighting personnel deployment trends in the western United States
Year: 2024
Projected increases in wildfire frequency, size, and severity may further stress already scarce firefighting resources in the western United States that are in high demand. Machine learning is a promising field with the ability to model firefighting resource usage without compromising dataset size or complexity. In this study, the Categorical Boosting (CatBoost) model was used with historical (2012-2020) wildfire data to train three models that calculate predicted daily counts of 1) total assigned personnel (total personnel), 2) assigned personnel that are at the fire (ground personnel), and…
Publication Type: Journal Article