ELM2.1-XGBfire1.0: improving wildfire prediction by integrating a machine learning fire model in a land surface model

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

doi:https://doi.org/10.5194/gmd-18-4103-2025

Articles | Volume 18, issue 13

https://doi.org/10.5194/gmd-18-4103-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-18-4103-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 13

Model description paper

|

04 Jul 2025

Model description paper |

| 04 Jul 2025

ELM2.1-XGBfire1.0: improving 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

Data sets

Simulated wildfire burned area over the CONUS during 2001–2020 DataHub https://doi.org/10.25584/2424127

tzhang-ccs/ML4ESM: ML4ESM_v1 (Version v1) T. Zhang https://doi.org/10.5281/zenodo.11005103

Machine learning (XGBoost) fire model for CONUS Y. Liu https://doi.org/10.5281/zenodo.13358187

Model code and software

Energy Exascale Earth System Model v2.1.0 E3SM Project https://doi.org/10.11578/E3SM/dc.20230110.5

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.