Preprints
https://doi.org/10.5194/gmd-2024-151
https://doi.org/10.5194/gmd-2024-151
Submitted as: model description paper
 | 
30 Aug 2024
Submitted as: model description paper |  | 30 Aug 2024
Status: a revised version of this preprint is currently under review for the journal GMD.

ML4Fire-XGBv1.0: Improving North American wildfire prediction by integrating a machine-learning fire model in a land surface model

Ye Liu, Huilin Huang, Sing-Chun Wang, Tao Zhang, Donghui Xu, and Yang Chen

Abstract. Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001–2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Ye Liu, Huilin Huang, Sing-Chun Wang, Tao Zhang, Donghui Xu, and Yang Chen

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2024-151', Anonymous Referee #1, 28 Sep 2024
  • RC2: 'Comment on gmd-2024-151', Matthew Kasoar, 29 Oct 2024
Ye Liu, Huilin Huang, Sing-Chun Wang, Tao Zhang, Donghui Xu, and Yang Chen
Ye Liu, Huilin Huang, Sing-Chun Wang, Tao Zhang, Donghui Xu, and Yang Chen

Viewed

Total article views: 440 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
256 77 107 440 6 4
  • HTML: 256
  • PDF: 77
  • XML: 107
  • Total: 440
  • BibTeX: 6
  • EndNote: 4
Views and downloads (calculated since 30 Aug 2024)
Cumulative views and downloads (calculated since 30 Aug 2024)

Viewed (geographical distribution)

Total article views: 429 (including HTML, PDF, and XML) Thereof 429 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 08 Dec 2024
Download
Short summary
This study integrates machine learning with a land surface model to improve wildfire predictions in North America. Traditional models struggle with accurately simulating burned areas due to simplified processes. By combining the predictive power of machine learning with a land model, our hybrid framework better captures fire dynamics. This approach enhances our understanding of wildfire behavior and aids in developing more effective climate and fire management strategies.