An efficient training scheme for supermodels

Schevenhoven, Francine J.; Selten, Frank M.

doi:https://doi.org/10.5194/esd-8-429-2017

Articles | Volume 8, issue 2

https://doi.org/10.5194/esd-8-429-2017

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

https://doi.org/10.5194/esd-8-429-2017

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

Articles | Volume 8, issue 2

Research article

|

28 Jun 2017

Research article |

| 28 Jun 2017

An efficient training scheme for supermodels

Francine J. Schevenhoven and Frank M. Selten

Download

Final revised paper (published on 28 Jun 2017)
Preprint (discussion started on 24 Jan 2017)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'esd-2017-6 review', Anonymous Referee #1, 19 Feb 2017
- AC1: 'Reply to Anonymous Referee #1', Francine Schevenhoven, 31 Mar 2017
RC2: 'Review of "An efficient training scheme that improves the forecast skill of a supermodel" by Francine Schevenhoven and Frank Selten Manuscript Number: esd-2017-6 by Reviewer Guannan Hu', Guannan Hu, 21 Feb 2017
- AC2: 'Reply to reviewer Guannan Hu', Francine Schevenhoven, 31 Mar 2017

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

ED: Reconsider after major revisions (31 Mar 2017) by Christian Franzke

AR by Francine Schevenhoven on behalf of the Authors (05 May 2017) Author's response Manuscript

ED: Publish as is (08 May 2017) by Christian Franzke

AR by Francine Schevenhoven on behalf of the Authors (15 May 2017)

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.