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

. Wildfire is an important ecosystem process, influencing land biogeophysicaland biogeochemical dynamics and atmospheric composition. Fire-driven loss ofvegetation cover, for example, directly modifies the surface energy budgetas a consequence of changing albedo, surface roughness, and partitioning ofsensible and latent heat fluxes. Carbon dioxide and methane emitted by firescontribute to a positive atmospheric forcing, whereas emissions ofcarbonaceous aerosols may contribute to surface cooling. Process-basedmodeling of wildfires in Earth system land models is challenging due tolimited understanding of human, climate, and ecosystem controls on firecounts, fire size, and burned area. Integration of mechanistic wildfiremodels within Earth system models requires careful parameter calibration,which is computationally expensive and subject to equifinality. To explorealternative approaches, we present a deep neural network (DNN) scheme thatsurrogates the process-based wildfire model with the Energy Exascale EarthSystem Model (E3SM) interface. The DNN wildfire model accurately simulatesobserved burned area with over 90 % higher accuracy with a large reductionin parameterization time compared with the current process-based wildfiremodel. The surrogate wildfire model successfully captured the observedmonthly regional burned area during validation period 2011 to 2015(coefficient of determination, R2=0.93). Since the DNN wildfiremodel has the same input and output requirements as the E3SM process-basedwildfire model, our results demonstrate the applicability of machinelearning for high accuracy and efficient large-scale land model developmentand predictions.

Building a machine learning surrogate model for wildfire activities within a global Earth system model