Natural Hazards and Earth System Sciences
Natural Hazards and Earth System Sciences
NHESS
Articles | Volume 26, issue 9
Articles | Volume 26, issue 9
https://doi.org/10.5194/nhess-26-4407-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/nhess-26-4407-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 26, issue 9
Research article
 | 
14 Sep 2026
Research article |  | 14 Sep 2026

Short-term drought forecasting in Iran using multi-source machine learning: an assessment of autoregressive, teleconnection-driven, and hybrid paradigms

Jun Jian, Peyman Mahmoudi, Pouria Jafari, Alireza Ghaemi, Jing Yang, and Fatemeh Firoozi

Viewed

Total article views: 2,218 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,175 942 101 2,218 212 84 166
  • HTML: 1,175
  • PDF: 942
  • XML: 101
  • Total: 2,218
  • Supplement: 212
  • BibTeX: 84
  • EndNote: 166
Views and downloads (calculated since 18 Feb 2026)
Cumulative views and downloads (calculated since 18 Feb 2026)

Viewed (geographical distribution)

Total article views: 2,218 (including HTML, PDF, and XML) Thereof 2,192 with geography defined and 26 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 14 Sep 2026
Download
Short summary
To improve drought early warnings, we tested if past drought patterns, global climate signals, or their combination best predict future droughts across Iran. Using thirty years of rainfall data and nine computer models, we found no single approach works everywhere. Combined methods excel in dry areas, while single methods suit coasts. This proves we must abandon uniform tools and build customized, location-specific forecasting systems to better protect communities from climate hazards.
Read more
Share
Altmetrics
Final-revised paper
Preprint