English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. Occurrences of devastating wildfires have been increasingin the United States for the past decades. While some environmentalcontrols, including weather, climate, and fuels, are known to play importantroles in controlling wildfires, the interrelationships between these factorsand wildfires are highly complex and may not be well represented bytraditional parametric regressions. Here we develop a model consisting ofmultiple machine learning algorithms to predict 0.5∘×0.5∘ griddedmonthly wildfire burned area over the south central United States during2002–2015 and then use this model to identify the relative importance of theenvironmental drivers on the burned area for both the winter–spring andsummer fire seasons of that region. The developed model alleviates the issueof unevenly distributed burned-area data, predicts burned grids with areaunder the curve (AUC) of 0.82 and 0.83 for the two seasons, and achievestemporal correlations larger than 0.5 for more than 70 % of the grids andspatial correlations larger than 0.5 (p&lt;0.01) for more than 60 %of the months. For the total burned area over the study domain, the modelcan explain 50 % and 79 % of the observed interannual variability forthe winter–spring and summer fire season, respectively. Variable importancemeasures indicate that relative humidity (RH) anomalies and precedingmonths' drought severity are the two most important predictor variablescontrolling the spatial and temporal variation in gridded burned area forboth fire seasons. The model represents the effect of climate variability byclimate-anomaly variables, and these variables are found to contribute themost to the magnitude of the total burned area across the whole domain forboth fire seasons. In addition, antecedent fuel amounts and conditions arefound to outweigh the weather effects on the amount of total burned area inthe winter–spring fire season, while fire weather is more important for thesummer fire season likely due to relatively sufficient vegetation in thisseason.

Quantifying the effects of environmental factors on wildfire burned area in the south central US using integrated machine learning techniques