Journal cover Journal topic
Earth System Dynamics An interactive open-access journal of the European Geosciences Union

Journal metrics

  • IF value: 3.635 IF 3.635
  • IF 5-year<br/> value: 3.869 IF 5-year
    3.869
  • CiteScore<br/> value: 4.15 CiteScore
    4.15
  • SNIP value: 0.995 SNIP 0.995
  • SJR value: 2.742 SJR 2.742
  • IPP value: 3.679 IPP 3.679
  • h5-index value: 21 h5-index 21
https://doi.org/10.5194/esd-2017-6
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.
Research article
24 Jan 2017
Review status
A revision of this discussion paper was accepted for the journal Earth System Dynamics (ESD) and is expected to appear here in due course.
An efficient training scheme that improves the forecast skill of a supermodel
Francine Schevenhoven1,2 and Frank Selten1 1Royal Netherlands Meteorological Institute, De Bilt, The Netherlands
2Geophysical Institute, University of Bergen, Bergen, Norway
Abstract. Weather and climate models have improved steadily over time as witnessed by objective skill scores, although significant model errors remain. Given these imperfect models, predictions might be improved by combining them dynamically into a so-called supermodel. In this paper a new training scheme to construct such a supermodel is explored using a technique called Cross Pollination in Time (CPT). In the CPT approach the models exchange states during the prediction. The number of possible predictions grows quickly with time and a strategy to retain only a small number of predictions, called pruning, needs to be developed. The method is explored using low-order dynamical systems and applied to a global atmospheric model. The results indicate that the CPT training is efficient and leads to a supermodel with improved forecast quality as compared to the individual models. Due to its computational efficiency, the technique is suited for application to state-of-the art high-dimensional weather and climate models.

Citation: Schevenhoven, F. and Selten, F.: An efficient training scheme that improves the forecast skill of a supermodel, Earth Syst. Dynam. Discuss., https://doi.org/10.5194/esd-2017-6, in review, 2017.
Francine Schevenhoven and Frank Selten
Francine Schevenhoven and Frank Selten

Viewed

Total article views: 373 (including HTML, PDF, and XML)

HTML PDF XML Total BibTeX EndNote
317 30 26 373 5 26

Views and downloads (calculated since 24 Jan 2017)

Cumulative views and downloads (calculated since 24 Jan 2017)

Viewed (geographical distribution)

Total article views: 373 (including HTML, PDF, and XML)

Thereof 371 with geography defined and 2 with unknown origin.

Country # Views %
  • 1

Saved

Discussed

Latest update: 24 Jun 2017
Publications Copernicus
Download
Short summary
Weather and climate models have improved steadily over time, but the models remain imperfect. Given these imperfect models, predictions might be improved by combining the models into a so-called supermodel. In this paper we show a new method to construct such a supermodel. The results indicate that the supermodel has superior forecast quality compared to the individual models.
Weather and climate models have improved steadily over time, but the models remain imperfect....
Share