Articles | Volume 15, issue 5
Geosci. Model Dev., 15, 1899–1911, 2022
https://doi.org/10.5194/gmd-15-1899-2022
Geosci. Model Dev., 15, 1899–1911, 2022
https://doi.org/10.5194/gmd-15-1899-2022

Model description paper 08 Mar 2022

Model description paper | 08 Mar 2022

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

Qing Zhu et al.

Data sets

Global Fire Emissions Database, Version 4: https://daac.ornl.gov/VEGETATION/guides/fire_emissions_v4.html J. T. Randerson, G. R. van der Werf, L. Giglio, G. J. Collatz, and P. S. Kasibhatla https://doi.org/10.3334/ORNLDAAC/1293

Fire_cci Burned Area dataset, Fire_CCI51 ESA https://geogra.uah.es/fire_cci/firecci51.php

Fire_cci long-term Burned Area dataset, Fire_CCILT11 ESA https://geogra.uah.es/fire_cci/fireccilt11.php

MODIS Collection 6 Active Fire Product User’s Guide Revision C L. Giglio, W. Schroeder, J. V. Hall, and C. O. Justice https://modis-fire.umd.edu/files/MODIS_C6_Fire_User_Guide_C.pdf

Global Fire Atlas FireAtlas https://www.globalfiredata.org/fireatlas.html

Model outputs: Quantitative assessment of fire and vegetation properties in historical simulations with fire-enabled vegetation models from the Fire Model Intercomparison Project Stijn Hantson, Sam Rabin, Douglas I. Kelley, Almut Arneth, Sandy P. Harrison, Sally Archibald, Dominique Bachelet, Matthew Forrest, Thomas Hickler, Silvia Kloster, Gitta Lasslop, Fang Li, Stephane Mangeon, Joe R. Melton, Lars Nieradzik, I. Colin Prentice, Tim Sheehan, Stephen Sitch, Lena Teckentrup, Apostolos Voulgarakis, and Chao Yue https://doi.org/10.5281/zenodo.3555562

Model code and software

Building a machine learning surrogate model for wildfire activities within a global earth system model Q. Zhu https://doi.org/10.5281/zenodo.5508795

Download
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.