Natural Hazards and Earth System Sciences
Natural Hazards and Earth System Sciences
NHESS
Articles | Volume 26, issue 7
Articles | Volume 26, issue 7
https://doi.org/10.5194/nhess-26-3417-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/nhess-26-3417-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 26, issue 7
Research article
 | 
22 Jul 2026
Research article |  | 22 Jul 2026

Deep Learning Emulation of Multivariate Climate Indices: A Case Study of the Fire Weather Index in the Iberian Peninsula

Óscar Mirones, Joaquín Bedia, Pedro M. M. Soares, José M. Gutiérrez, and Jorge Baño-Medina

Viewed

Total article views: 10,089 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
8,307 1,382 400 10,089 447 472
  • HTML: 8,307
  • PDF: 1,382
  • XML: 400
  • Total: 10,089
  • BibTeX: 447
  • EndNote: 472
Views and downloads (calculated since 10 Jul 2025)
Cumulative views and downloads (calculated since 10 Jul 2025)

Viewed (geographical distribution)

Total article views: 10,089 (including HTML, PDF, and XML) Thereof 10,011 with geography defined and 78 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 04 Nov 2026
Download
Short summary
Wildfire danger is usually measured with a formula needing weather data from a specific time of day, often missing in climate simulations. Scientists have relied on a rough substitute that can be inaccurate. We trained artificial intelligence models on Iberian Peninsula weather records to recreate the proper measure using only common daily data. This proved far more accurate than the usual substitute, even without rainfall data, easing wildfire risk assessment for climate research and planning.
Read more
Share
Altmetrics
Final-revised paper
Preprint