Submitted as: model description paper 23 Apr 2021

Submitted as: model description paper | 23 Apr 2021

Review status: this preprint is currently under review for the journal GMD.

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

Qing Zhu1, Fa Li1,2, William J. Riley1, Li Xu3, Lei Zhao4, Kunxiaojia Yuan1,2, Huayi Wu2, Jianya Gong5, and James T. Randerson3 Qing Zhu et al.
  • 1Climate and Ecosystem Sciences Division, Climate Sciences Department, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
  • 2State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China
  • 3Department of Earth System Science, University of California Irvine, Irvine, CA, USA
  • 4Department of Civil and Environmental Engineering, University of Illinois Urbana-Champaign, Champaign, IL, USA
  • 5School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China

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.

Qing Zhu et al.

Status: open (until 18 Jun 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Qing Zhu et al.

Qing Zhu et al.


Total article views: 230 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
172 55 3 230 1 2
  • HTML: 172
  • PDF: 55
  • XML: 3
  • Total: 230
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 23 Apr 2021)
Cumulative views and downloads (calculated since 23 Apr 2021)

Viewed (geographical distribution)

Total article views: 204 (including HTML, PDF, and XML) Thereof 204 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 14 May 2021
Short summary
Wildfire is a devastating earth system process that burns about 500 million hectares of land each year. It wipes out vegetation including trees, shrubs, and grasses, and causes large losses of economic assets. However, modeling the spatial distribution and temporal changes of wildfire activities at a global scale is challenging. This study built a machine learning-based wildfire surrogate model within an existing earth system model and achieved high accuracy.