Fire weather indices tailored to regional patterns outperform global models

Abstract Fire weather indices (FWIs) are widely used to assess wildfire risk, but are typically designed for specific regions and not adapted globally. Here, we present a systematic effort to generate country-specific FWIs that capture regional fire-weather patterns. We evaluate three widely used in...

Full description

Saved in:
Bibliographic Details
Main Authors: Assaf Shmuel, Teddy Lazebnik, Eyal Heifetz, Oren Glickman, Colin Price
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Natural Hazards
Online Access:https://doi.org/10.1038/s44304-025-00126-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333793843838976
author Assaf Shmuel
Teddy Lazebnik
Eyal Heifetz
Oren Glickman
Colin Price
author_facet Assaf Shmuel
Teddy Lazebnik
Eyal Heifetz
Oren Glickman
Colin Price
author_sort Assaf Shmuel
collection DOAJ
description Abstract Fire weather indices (FWIs) are widely used to assess wildfire risk, but are typically designed for specific regions and not adapted globally. Here, we present a systematic effort to generate country-specific FWIs that capture regional fire-weather patterns. We evaluate three widely used indices across countries, finding that the Canadian FWI performs best overall (ROC AUC of 0.69). Tailoring the index to each country with a Genetic Algorithm significantly improves its accuracy, raising the ROC AUC from 0.69 to 0.79. To further improve accuracy while maintaining interpretability, we develop a single Decision Tree model per country, achieving an ROC AUC of 0.86. Attempts to develop a single global Decision Tree yielded substantially lower accuracy, highlighting the limitations of universal models and the importance of capturing regional characteristics such as weather patterns, vegetation types, and topography for accurately predicting wildfire risk. Adapting FWIs regionally is crucial under accelerating climate change conditions.
format Article
id doaj-art-7835c3b254e14a9987fa3699884dccd2
institution Kabale University
issn 2948-2100
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Natural Hazards
spelling doaj-art-7835c3b254e14a9987fa3699884dccd22025-08-20T03:45:45ZengNature Portfolionpj Natural Hazards2948-21002025-07-01211910.1038/s44304-025-00126-yFire weather indices tailored to regional patterns outperform global modelsAssaf Shmuel0Teddy Lazebnik1Eyal Heifetz2Oren Glickman3Colin Price4Department of Geophysics, Tel Aviv UniversityDepartment of Information Systems, University of HaifaDepartment of Geophysics, Tel Aviv UniversityDepartment of Computer Science, Bar Ilan UniversityDepartment of Geophysics, Tel Aviv UniversityAbstract Fire weather indices (FWIs) are widely used to assess wildfire risk, but are typically designed for specific regions and not adapted globally. Here, we present a systematic effort to generate country-specific FWIs that capture regional fire-weather patterns. We evaluate three widely used indices across countries, finding that the Canadian FWI performs best overall (ROC AUC of 0.69). Tailoring the index to each country with a Genetic Algorithm significantly improves its accuracy, raising the ROC AUC from 0.69 to 0.79. To further improve accuracy while maintaining interpretability, we develop a single Decision Tree model per country, achieving an ROC AUC of 0.86. Attempts to develop a single global Decision Tree yielded substantially lower accuracy, highlighting the limitations of universal models and the importance of capturing regional characteristics such as weather patterns, vegetation types, and topography for accurately predicting wildfire risk. Adapting FWIs regionally is crucial under accelerating climate change conditions.https://doi.org/10.1038/s44304-025-00126-y
spellingShingle Assaf Shmuel
Teddy Lazebnik
Eyal Heifetz
Oren Glickman
Colin Price
Fire weather indices tailored to regional patterns outperform global models
npj Natural Hazards
title Fire weather indices tailored to regional patterns outperform global models
title_full Fire weather indices tailored to regional patterns outperform global models
title_fullStr Fire weather indices tailored to regional patterns outperform global models
title_full_unstemmed Fire weather indices tailored to regional patterns outperform global models
title_short Fire weather indices tailored to regional patterns outperform global models
title_sort fire weather indices tailored to regional patterns outperform global models
url https://doi.org/10.1038/s44304-025-00126-y
work_keys_str_mv AT assafshmuel fireweatherindicestailoredtoregionalpatternsoutperformglobalmodels
AT teddylazebnik fireweatherindicestailoredtoregionalpatternsoutperformglobalmodels
AT eyalheifetz fireweatherindicestailoredtoregionalpatternsoutperformglobalmodels
AT orenglickman fireweatherindicestailoredtoregionalpatternsoutperformglobalmodels
AT colinprice fireweatherindicestailoredtoregionalpatternsoutperformglobalmodels