Reply on RC2

Qing Zhu

doi:10.5194/gmd-2021-83-ac2

Abstract

Wildfire is an important ecosystem process, influencing land biogeophysical and biogeochemical dynamics and atmospheric composition. Fire-driven loss of vegetation cover, for example, directly modifies the surface energy budget as a consequence of changing albedo, surface roughness, and partitioning of sensible and latent heat fluxes. Carbon dioxide and methane emitted by fires contribute to a positive atmospheric forcing, whereas emissions of carbonaceous aerosols may contribute to surface cooling. Process-based modeling of wildfires in earth system land models is challenging due to limited understanding of human, climate, and ecosystem controls on fire number, fire size, and burned area. Integration of mechanistic wildfire models within Earth system models requires careful parameter calibration, which is computationally expensive and subject to equifinality. To explore alternative approaches, we present a deep neural network (DNN) scheme that surrogates the process-based wildfire model within the Energy Exascale Earth System Model (E3SM). The DNN wildfire model accurately simulates the observed burned area with over 90 % higher accuracy with a large reduction in parameterization time compared with the current process-based wildfire model. The surrogate wildfire model successfully captured global dynamics of wildfire burned areas between years 2011 and 2015 (R2 = 0.93). Since the DNN wildfire model has the same input and output requirements as the E3SM process-based wildfire model, our results demonstrate the applicability of machine learning for high accuracy and efficient large-scale land model development and predictions.

Highlights

Wildfires burn ~500 million hectares of vegetated land surface each year, which significantly modifies the physical properties and biogeochemical cycles of terrestrial ecosystems [Andela et al, 2017; Bond-Lamberty et al, 2007; Pellegrini et al, 2018; Randerson et al, 2006]
We develop a machine learning wildfire model using the process representation of wildfire in the Energy Exascale Earth System Model (E3SM) land model (ELMv1) [Zhu et al, 2019] the observationally-inferred Global Fire Emissions Database v4 (GFEDv4), and a deep neural network approach [Goodfellow et al, 2016]
We developed the new fire model in two steps: (1) surrogating BASE-Fire with a deep neural network (DNN) approach and (2) improving that surrogate model using the Global Fire

Summary

Introduction

Wildfires burn ~500 million hectares of vegetated land surface each year, which significantly modifies the physical properties and biogeochemical cycles of terrestrial ecosystems [Andela et al, 2017; Bond-Lamberty et al, 2007; Pellegrini et al, 2018; Randerson et al, 2006]. Surface litter, and coarse woody debris are directly combusted and removed by wildfire [Harden et al, 2006; Walker et al, 2019]. It has been suggested that global forest would double if fire were eliminated [Bond et al, 2005]. Biomass burning emits a large amount of fine particulate matter that contributes to about 30% of cloud condensation nuclei globally [Day, 2004]. Nitrogen mineralization, and the richness and diversity of soil fungal communities [Oliver et al, 2015]

Objectives

Methods

Results

Conclusion