Hydrology and Earth System Sciences
Hydrology and Earth System Sciences
HESS
Articles | Volume 26, issue 21
Articles | Volume 26, issue 21
https://doi.org/10.5194/hess-26-5449-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-26-5449-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 26, issue 21
Research article
 | 
01 Nov 2022
Research article |  | 01 Nov 2022

Using a long short-term memory (LSTM) neural network to boost river streamflow forecasts over the western United States

Kieran M. R. Hunt, Gwyneth R. Matthews, Florian Pappenberger, and Christel Prudhomme

Viewed

Total article views: 8,788 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
6,218 2,442 128 8,788 113 134
  • HTML: 6,218
  • PDF: 2,442
  • XML: 128
  • Total: 8,788
  • BibTeX: 113
  • EndNote: 134
Views and downloads (calculated since 08 Feb 2022)
Cumulative views and downloads (calculated since 08 Feb 2022)

Viewed (geographical distribution)

Total article views: 8,788 (including HTML, PDF, and XML) Thereof 8,512 with geography defined and 276 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 15 Nov 2025
Download
Short summary
In this study, we use three models to forecast river streamflow operationally for 13 months (September 2020 to October 2021) at 10 gauges in the western US. The first model is a state-of-the-art physics-based streamflow model (GloFAS). The second applies a bias-correction technique to GloFAS. The third is a type of neural network (an LSTM). We find that all three are capable of producing skilful forecasts but that the LSTM performs the best, with skilful 5 d forecasts at nine stations.
Read more
Share