Comparison of cross-validation and bootstrap aggregating for building a seasonal  streamflow forecast model

Schick, Simon; Rössler, Ole; Weingartner, Rolf

doi:https://doi.org/10.5194/piahs-374-159-2016

Articles | Volume 374

https://doi.org/10.5194/piahs-374-159-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

https://doi.org/10.5194/piahs-374-159-2016

© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

Articles | Volume 374

17 Oct 2016

| 17 Oct 2016

Comparison of cross-validation and bootstrap aggregating for building a seasonal streamflow forecast model

Simon Schick, Ole Rössler, and Rolf Weingartner

Data sets

Streamﬂow monitoring Austria, Bundesministerium für Land- und Forstwirtschaft, Umwelt und Wasserwirtschaft BMLFUW http://ehyd.gv.at/

Corine Land Cover 2006 raster data CORINE http://www.eea.europa.eu/data-and-maps/data/corine-land-cover-2006-raster-3

Daily temperature and precipitation fields in Europe E-OBS http://www.ecad.eu/download/ensembles/ensembles.php

Digital Elevation Model over Europe EU-DEM http://www.eea.europa.eu/data-and-maps/data/eu-dem

Streamflow monitoring Bayern GKDB http://www.gkd.bayern.de/fluesse/abfluss/karten/index.php?thema=gkd&rubrik=fluesse&produkt=abfluss&gknr=0

Short summary

In water resources management, planning at the seasonal time scale is confronted with large uncertainties. Key variables are often unknown or hard to forecast, e.g. precipitation of the next three months. In the present study, we try to highlight some aspects concerning the development of a model faced with these uncertainties. Using the example of statistical streamflow forecasts, the results of the study indicate that the forecast accuracy is improved by the combination of several models.