Preprints
https://doi.org/10.5194/gmd-2022-195
https://doi.org/10.5194/gmd-2022-195
Submitted as: model description paper
11 Aug 2022
Submitted as: model description paper | 11 Aug 2022
Status: this preprint is currently under review for the journal GMD.

AttentionFire_v1.0: interpretable machine learning fire model for burned area predictions over tropics

Fa Li1,2, Qing Zhu1, William Riley1, Lei Zhao3, Li Xu4, Kunxiaojia Yuan1,2, Min Chen5, Huayi Wu2, Zhipeng Gui6, Jianya Gong6, and James Randerson4 Fa Li 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 Civil and Environmental Engineering, University of Illinois Urbana Champaign, Champaign, IL, USA
  • 4Department of Earth System Science, University of California Irvine, Irvine, CA, USA
  • 5Department of Forest and Wildlife Ecology, University of Wisconsin-Madison, Madison, WI, USA
  • 6School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China

Abstract. African and South American (ASA) wildfires account for more than 70 % of global burned areas and have strong connection to local climate for sub-seasonal to seasonal wildfire dynamics. However, representation of the wildfire-climate relationship remains challenging, due to spatiotemporally heterogenous responses of wildfires to climate variability and human influences. Here, we developed an interpretable Machine Learning (ML) fire model (AttentionFire_v1.0) to resolve the complex spatial- heterogenous and time-lagged controls from climate on burned area and to better predict burned areas over ASA regions. Our ML fire model substantially improved predictability of burned area for both spatial and temporal dynamics compared with five commonly used machine learning models. More importantly, the model revealed strong time-lagged control from climate wetness on the burned areas. The model also predicted that under a high emission future climate scenario, the recently observed declines in burned area will reverse in South America in the near future due to climate changes. Our study provides reliable and interpretable fire model and highlights the importance of lagged wildfire-climate relationships in historical and future predictions.

Fa Li et al.

Status: open (until 21 Oct 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2022-195', Anonymous Referee #1, 25 Aug 2022 reply

Fa Li et al.

Viewed

Total article views: 440 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
341 92 7 440 27 3 2
  • HTML: 341
  • PDF: 92
  • XML: 7
  • Total: 440
  • Supplement: 27
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 11 Aug 2022)
Cumulative views and downloads (calculated since 11 Aug 2022)

Viewed (geographical distribution)

Total article views: 385 (including HTML, PDF, and XML) Thereof 385 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 28 Sep 2022
Download
Short summary
In this work, we developed an interpretable machine learning model to predict sub-seasonal and near future wildfire burned area over African and South American regions. We found strong time-lagged controls (up to 6–8 month) from local climate wetness on burned areas. A skillful use of such time-lagged controls in machine learning model result in high accurate predictions of wildfire burned area, also will help develop relevant early warming and management system for tropical wildfire.