Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311481142> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4311481142 abstract "<strong class=journal-contentHeaderColor>Abstract.</strong> The annual area burned due to wildfires in the western United States (WUS) increased by more than 300 % between 1984 and 2020. However, accounting for the nonlinear, spatially heterogeneous interactions between climate, vegetation, and human predictors driving the trends in fire frequency and sizes at different spatial scales remains a challenging problem for statistical fire models. Here we introduce a novel stochastic machine learning (SML) framework, SMLFire1.0, to model observed fire frequencies and sizes in 12 km x 12 km grid cells across the WUS. This framework is implemented using Mixture Density Networks trained on a wide suite of input predictors. The modeled WUS fire frequency corresponds well with observations at both monthly (<em>r </em>= 0.94) and annual (<em>r </em>= 0.85) timescales, as do the monthly (<em>r </em>= 0.90) and annual (<em>r </em>= 0.88) area burned. Moreover, the annual time series of both fire variables exhibit strong correlations (<em>r</em> ≥ 0.6) in 16 out of 18 ecoregions. Our ML model captures the interannual variability and the distinct multidecade increases in annual area burned for both forested and non-forested ecoregions. Evaluating predictor importance with Shapley additive explanations, we find that fire month vapor pressure deficit (VPD) is the dominant driver of fire frequencies and sizes across the WUS, followed by 1000-hour dead fuel moisture (FM1000), total monthly precipitation (Prec), mean daily maximum temperature (Tmax), and fraction of grassland cover in a grid cell. Our findings serve as a promising use case of ML techniques for wildfire prediction in particular and extreme event modeling more broadly. They also highlight the power of ML driven parameterizations for potential implementation in the fire modules of Dynamic Global Vegetation Models (DGVMs) and Earth System Models (ESMs)." @default.
- W4311481142 created "2022-12-26" @default.
- W4311481142 date "2022-12-14" @default.
- W4311481142 modified "2023-09-30" @default.
- W4311481142 title "Comment on egusphere-2022-1148" @default.
- W4311481142 doi "https://doi.org/10.5194/egusphere-2022-1148-rc2" @default.
- W4311481142 hasPublicationYear "2022" @default.
- W4311481142 type Work @default.
- W4311481142 citedByCount "0" @default.
- W4311481142 crossrefType "peer-review" @default.
- W4311481142 hasBestOaLocation W43114811421 @default.
- W4311481142 hasConcept C100970517 @default.
- W4311481142 hasConcept C107054158 @default.
- W4311481142 hasConcept C110872660 @default.
- W4311481142 hasConcept C127313418 @default.
- W4311481142 hasConcept C13280743 @default.
- W4311481142 hasConcept C142724271 @default.
- W4311481142 hasConcept C14331020 @default.
- W4311481142 hasConcept C153294291 @default.
- W4311481142 hasConcept C157517311 @default.
- W4311481142 hasConcept C183688256 @default.
- W4311481142 hasConcept C187691185 @default.
- W4311481142 hasConcept C18903297 @default.
- W4311481142 hasConcept C205649164 @default.
- W4311481142 hasConcept C2775835988 @default.
- W4311481142 hasConcept C2776133958 @default.
- W4311481142 hasConcept C2780648208 @default.
- W4311481142 hasConcept C2983008078 @default.
- W4311481142 hasConcept C39432304 @default.
- W4311481142 hasConcept C4792198 @default.
- W4311481142 hasConcept C49204034 @default.
- W4311481142 hasConcept C59822182 @default.
- W4311481142 hasConcept C71924100 @default.
- W4311481142 hasConcept C86803240 @default.
- W4311481142 hasConcept C89736061 @default.
- W4311481142 hasConcept C91586092 @default.
- W4311481142 hasConceptScore W4311481142C100970517 @default.
- W4311481142 hasConceptScore W4311481142C107054158 @default.
- W4311481142 hasConceptScore W4311481142C110872660 @default.
- W4311481142 hasConceptScore W4311481142C127313418 @default.
- W4311481142 hasConceptScore W4311481142C13280743 @default.
- W4311481142 hasConceptScore W4311481142C142724271 @default.
- W4311481142 hasConceptScore W4311481142C14331020 @default.
- W4311481142 hasConceptScore W4311481142C153294291 @default.
- W4311481142 hasConceptScore W4311481142C157517311 @default.
- W4311481142 hasConceptScore W4311481142C183688256 @default.
- W4311481142 hasConceptScore W4311481142C187691185 @default.
- W4311481142 hasConceptScore W4311481142C18903297 @default.
- W4311481142 hasConceptScore W4311481142C205649164 @default.
- W4311481142 hasConceptScore W4311481142C2775835988 @default.
- W4311481142 hasConceptScore W4311481142C2776133958 @default.
- W4311481142 hasConceptScore W4311481142C2780648208 @default.
- W4311481142 hasConceptScore W4311481142C2983008078 @default.
- W4311481142 hasConceptScore W4311481142C39432304 @default.
- W4311481142 hasConceptScore W4311481142C4792198 @default.
- W4311481142 hasConceptScore W4311481142C49204034 @default.
- W4311481142 hasConceptScore W4311481142C59822182 @default.
- W4311481142 hasConceptScore W4311481142C71924100 @default.
- W4311481142 hasConceptScore W4311481142C86803240 @default.
- W4311481142 hasConceptScore W4311481142C89736061 @default.
- W4311481142 hasConceptScore W4311481142C91586092 @default.
- W4311481142 hasLocation W43114811421 @default.
- W4311481142 hasOpenAccess W4311481142 @default.
- W4311481142 hasPrimaryLocation W43114811421 @default.
- W4311481142 hasRelatedWork W1933164979 @default.
- W4311481142 hasRelatedWork W2014967464 @default.
- W4311481142 hasRelatedWork W2107686664 @default.
- W4311481142 hasRelatedWork W2161549781 @default.
- W4311481142 hasRelatedWork W2169002664 @default.
- W4311481142 hasRelatedWork W2370750659 @default.
- W4311481142 hasRelatedWork W2388996159 @default.
- W4311481142 hasRelatedWork W2996465968 @default.
- W4311481142 hasRelatedWork W3151903044 @default.
- W4311481142 hasRelatedWork W4200229308 @default.
- W4311481142 isParatext "false" @default.
- W4311481142 isRetracted "false" @default.
- W4311481142 workType "peer-review" @default.