EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fire Intensity and spRead forecAst (FIRA): A Machine Learning Based Fire Spread Prediction Model for Air Quality Forecasting Application

Wei-Ting Hung iD, Barry Baker iD, Patrick C Campbell iD, Youhua Tang iD, Ravan Ahmadov, Johana Romero-Alvarez, Haiqin Li iD, Jordan Schnell iD

GeoHealth · 2025-03 · 9 (3)

DOI: 10.1029/2024gh001253 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GeoHealth, online erschienen am 22.03.2025. Verfasst von Wei-Ting Hung und 7 weiteren Autor:innen. Beteiligte Einrichtung: Air Resources Laboratory National Oceanic and Atmospheric Administration College Park MD USA. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NOAA Weather Program Office, Oak Ridge Associated Universities, George Mason University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fire activities introduce hazardous impacts on the environment and public health by emitting various chemical species into the atmosphere. Most operational air quality forecast (AQF) models estimate smoke emissions based on the latest available satellite fire products, which may not represent real‐time fire behaviors without considering fire spread. Hence, a novel machine learning (ML) based fire spread forecast model, the Fire Intensity and spRead forecAst (FIRA), is developed for AQF model applications. FIRA aims to improve the performance of AQF models by providing realistic, dynamic fire characteristics including the spatial distribution and intensity of fire radiative power (FRP). In this study, data sets in 2020 over the continental United States (CONUS) and a historical California fire in 2024 are used for model training and evaluation. For application assessment, FIRA FRP predictions are applied to the Unified Forecast System coupled with smoke (UFS‐Smoke) model as inputs, focusing on a California fire case in September 2020. Results show that FIRA captures fire spread with R‐squared ( R 2 ) near 0.7 and good spatial similarity (∼95%). The comparison between UFS‐Smoke simulations using near‐real‐time fire products and FIRA FRP predictions show good agreements, indicating that FIRA can accurately represent future fire activities. Although FIRA generally underestimates fire intensity, the uncertainties can be mitigated by applying scaling factors to FRP values. Use of the scaled FIRA largely outperforms the experimental UFS‐Smoke model in predicting aerosol optical depth and the three‐dimensional smoke contents, while also demonstrating the ability to improve surface fine particulate matter (PM 2.5 ) concentrations affected by fires.

Schlagwörter

Stichwörter der Autor:innen

monitoring, forecasting, predictionpollution: urban and regionalwildland fire model

Autor:innen und Institutionen

  • Air Resources Laboratory National Oceanic and Atmospheric Administration College Park MD USA.
  • Cooperative Institute for Satellite and Earth System Studies University of Maryland College Park MD USA.
  • Center for Spatial Information Science and Systems George Mason University Fairfax VA USA.
  • Global Systems Laboratory National Oceanic and Atmospheric Administration Boulder CO USA.
  • Cooperative Institute for Research in Environmental Sciences University of Colorado Boulder CO USA.

ORCID-Profile: Wei-Ting Hung, Barry Baker, Patrick C Campbell, Youhua Tang, Haiqin Li, Jordan Schnell

Förderung

  • NOAA Weather Program Office
  • Oak Ridge Associated Universities
  • George Mason University
  • National Oceanic and Atmospheric Administration

Zitieren

APA

Hung, W. T., Baker, B., Campbell, P. C., Tang, Y., Ahmadov, R., Romero-Alvarez, J., Li, H., & Schnell, J. (2025). Fire Intensity and spRead forecAst (FIRA): A Machine Learning Based Fire Spread Prediction Model for Air Quality Forecasting Application. GeoHealth, 9(3). https://doi.org/10.1029/2024gh001253

Vancouver

Hung WT, Baker B, Campbell PC, Tang Y, Ahmadov R, Romero-Alvarez J, et al. Fire Intensity and spRead forecAst (FIRA): A Machine Learning Based Fire Spread Prediction Model for Air Quality Forecasting Application. GeoHealth. 2025;9(3). doi:10.1029/2024gh001253

BibTeX
@article{Hung2025,
  author = {Hung, Wei-Ting and Baker, Barry and Campbell, Patrick C and Tang, Youhua and Ahmadov, Ravan and Romero-Alvarez, Johana and Li, Haiqin and Schnell, Jordan},
  title = {Fire Intensity and spRead forecAst (FIRA): A Machine Learning Based Fire Spread Prediction Model for Air Quality Forecasting Application},
  journal = {GeoHealth},
  year = {2025},
  volume = {9},
  number = {3},
  doi = {10.1029/2024gh001253}
}
Kostenlos starten →