Articles | Volume 45
https://doi.org/10.5194/adgeo-45-201-2018
https://doi.org/10.5194/adgeo-45-201-2018
27 Aug 2018
 | 27 Aug 2018

Evaluation of random forests and Prophet for daily streamflow forecasting

Georgia A. Papacharalampous and Hristos Tyralis

Viewed

Total article views: 4,786 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
3,667 1,000 119 4,786 271 128 185
  • HTML: 3,667
  • PDF: 1,000
  • XML: 119
  • Total: 4,786
  • Supplement: 271
  • BibTeX: 128
  • EndNote: 185
Views and downloads (calculated since 27 Aug 2018)
Cumulative views and downloads (calculated since 27 Aug 2018)

Viewed (geographical distribution)

Total article views: 4,606 (including HTML, PDF, and XML) Thereof 4,574 with geography defined and 32 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 29 Jan 2026
Download
Short summary
The predictive performance of random forests (a machine learning algorithm) and three configurations of Prophet (a method largely implemented in Facebook) is assessed in daily streamflow forecasting in a river in the US. Random forests perform better compared to the utilized benchmarks, i.e. a naïve method and a multiple regression linear model, while Prophet's performance is subject to improvements. Random forests are recommended for daily streamflow forecasting.
Share