Articles | Volume 25, issue 6
Hydrol. Earth Syst. Sci., 25, 2997–3015, 2021
https://doi.org/10.5194/hess-25-2997-2021
Hydrol. Earth Syst. Sci., 25, 2997–3015, 2021
https://doi.org/10.5194/hess-25-2997-2021

Research article 03 Jun 2021

Research article | 03 Jun 2021

Evaluation of random forests for short-term daily streamflow forecasting in rainfall- and snowmelt-driven watersheds

Leo Triet Pham et al.

Viewed

Total article views: 47,784 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
24,470 23,288 26 47,784 89 25 28
  • HTML: 24,470
  • PDF: 23,288
  • XML: 26
  • Total: 47,784
  • Supplement: 89
  • BibTeX: 25
  • EndNote: 28
Views and downloads (calculated since 23 Jun 2020)
Cumulative views and downloads (calculated since 23 Jun 2020)

Viewed (geographical distribution)

Total article views: 42,929 (including HTML, PDF, and XML) Thereof 42,926 with geography defined and 3 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 20 Oct 2021
Download
Short summary
Model evaluation metrics suggest that RF performs better in snowmelt-driven watersheds. The largest improvements in forecasts compared to benchmark models are found among rainfall-driven watersheds. RF performance deteriorates with increases in catchment slope and soil sandiness. We note disagreement between two popular measures of RF variable importance and recommend jointly considering these measures with the physical processes under study.