Articles | Volume 26, issue 1
https://doi.org/10.5194/hess-26-129-2022
https://doi.org/10.5194/hess-26-129-2022
Research article
 | 
12 Jan 2022
Research article |  | 12 Jan 2022

Parsimonious statistical learning models for low-flow estimation

Johannes Laimighofer, Michael Melcher, and Gregor Laaha

Viewed

Total article views: 2,362 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,872 460 30 2,362 29 20
  • HTML: 1,872
  • PDF: 460
  • XML: 30
  • Total: 2,362
  • BibTeX: 29
  • EndNote: 20
Views and downloads (calculated since 22 Sep 2021)
Cumulative views and downloads (calculated since 22 Sep 2021)

Viewed (geographical distribution)

Total article views: 2,362 (including HTML, PDF, and XML) Thereof 2,247 with geography defined and 115 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 30 Sep 2023
Download
Short summary
This study aims to predict long-term averages of low flow on a hydrologically diverse dataset in Austria. We compared seven statistical learning methods and included a backward variable selection approach. We found that separating the low-flow processes into winter and summer low flows leads to good performance for all the models. Variable selection results in more parsimonious and more interpretable models. Linear approaches for prediction and variable selection are sufficient for our dataset.