Technical note: Combining quantile forecasts and predictive distributions of streamflows

Bogner, Konrad; Liechti, Katharina; Zappa, Massimiliano

doi:https://doi.org/10.5194/hess-21-5493-2017

Articles | Volume 21, issue 11

https://doi.org/10.5194/hess-21-5493-2017

© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.

https://doi.org/10.5194/hess-21-5493-2017

© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.

Articles | Volume 21, issue 11

Technical note

|

08 Nov 2017

Technical note |

| 08 Nov 2017

Technical note: Combining quantile forecasts and predictive distributions of streamflows

Konrad Bogner, Katharina Liechti, and Massimiliano Zappa

Data sets

Quantile regression neural networks: Implementation in R and application to precipitation downscaling A. J. Cannon https://doi.org/10.1016/j.cageo.2010.07.005

Using Bayesian Model Averaging to Calibrate Forecast Ensembles A. Raftery, T. Gneiting, F. Balabdaoui, and M. Polakowski https://doi.org/10.1175/MWR2906.1

Short summary

The enhanced availability of many different weather prediction systems nowadays makes it very difficult for flood and water resource managers to choose the most reliable and accurate forecast. In order to circumvent this problem of choice, different approaches for combining this information have been applied at the Sihl River (CH) and the results have been verified. The outcome of this study highlights the importance of forecast combination in order to improve the quality of forecast systems.