Hydrology and Earth System Sciences
Hydrology and Earth System Sciences
HESS
Articles | Volume 30, issue 11
Articles | Volume 30, issue 11
https://doi.org/10.5194/hess-30-3623-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-30-3623-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 30, issue 11
Research article
 | 
15 Jun 2026
Research article |  | 15 Jun 2026

Which strategy to improve the performances of an LSTM-based model for extreme stream temperature values?

Mohamed Saadi, Louis Guichard, Gabrielle Cognot, Laurent Labbouz, and Hélène Roux

Viewed

Total article views: 8,518 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
7,493 792 233 8,518 253 290
  • HTML: 7,493
  • PDF: 792
  • XML: 233
  • Total: 8,518
  • BibTeX: 253
  • EndNote: 290
Views and downloads (calculated since 30 Jul 2025)
Cumulative views and downloads (calculated since 30 Jul 2025)

Viewed (geographical distribution)

Total article views: 8,518 (including HTML, PDF, and XML) Thereof 8,512 with geography defined and 6 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 15 Jun 2026
Download
Short summary
LSTM (Long Short-Term Memory) networks are excellent deep-learning tools to reproduce stream temperature observations, but their performances over the range of extreme (summer) stream temperature values have been overlooked. We tested strategies to improve the LSTM performances over the highest 10 % values of stream temperature observations. We found that the best strategy is to train the LSTM models at several locations with input variables that include static, catchment and reach attributes.
Read more
Share