Journal cover Journal topic
Advances in Geosciences An open-access journal for refereed proceedings and special publications
Journal topic

Journal metrics

Journal metrics

  • CiteScore value: 1.02 CiteScore 1.02
  • SNIP value: 0.614 SNIP 0.614
  • SJR value: 0.435 SJR 0.435
  • IPP value: 0.97 IPP 0.97
  • h5-index value: 11 h5-index 11
  • Scimago H index value: 32 Scimago H index 32
Volume 45 | Copyright
Adv. Geosci., 45, 201-208, 2018
https://doi.org/10.5194/adgeo-45-201-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  27 Aug 2018

27 Aug 2018

Evaluation of random forests and Prophet for daily streamflow forecasting

Georgia A. Papacharalampous1,* and Hristos Tyralis2,* Georgia A. Papacharalampous and Hristos Tyralis
  • 1Department of Water Resources and Environmental Engineering, National Technical University of Athens, Zografou, 157 80, Greece
  • 2Air Force Support Command, Hellenic Air Force, Elefsina, 192 00, Greece
  • *These authors contributed equally to this work.

Abstract. We assess the performance of random forests and Prophet in forecasting daily streamflow up to seven days ahead in a river in the US. Both the assessed forecasting methods use past streamflow observations, while random forests additionally use past precipitation information. For benchmarking purposes we also implement a naïve method based on the previous streamflow observation, as well as a multiple linear regression model utilizing the same information as random forests. Our aim is to illustrate important points about the forecasting methods when implemented for the examined problem. Therefore, the assessment is made in detail at a sufficient number of starting points and for several forecast horizons. The results suggest that random forests perform better in general terms, while Prophet outperforms the naïve method for forecast horizons longer than three days. Finally, random forests forecast the abrupt streamflow fluctuations more satisfactorily than the three other methods.

Download & links
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.
The predictive performance of random forests (a machine learning algorithm) and three...
Citation
Share