Challenges and design choices for global weather and climate models based on machine learning

Dueben, Peter D.; Bauer, Peter

doi:https://doi.org/10.5194/gmd-11-3999-2018

Articles | Volume 11, issue 10

https://doi.org/10.5194/gmd-11-3999-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-11-3999-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 11, issue 10

Development and technical paper

|

01 Oct 2018

Development and technical paper |

| 01 Oct 2018

Challenges and design choices for global weather and climate models based on machine learning

Peter D. Dueben and Peter Bauer

Download

Final revised paper (published on 01 Oct 2018)
Supplement to the final revised paper
Preprint (discussion started on 28 Jun 2018)
Supplement to the preprint

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC1: 'Manuscript review', Anonymous Referee #1, 17 Jul 2018
RC2: 'Challenges and design choices for global weather and climate models based on machine learning', Anonymous Referee #2, 24 Jul 2018
AC1: 'Response to the first round of reviews', Peter Düben, 08 Aug 2018

Peer-review completion

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

AR by Peter Düben on behalf of the Authors (30 Aug 2018) Manuscript

ED: Publish as is (12 Sep 2018) by David Topping

AR by Peter Düben on behalf of the Authors (14 Sep 2018)

Short summary

We discuss the question of whether weather forecast models that are based on deep learning and trained on atmospheric data can compete with conventional weather and climate models that are based on physical principles and the basic equations of motion. We discuss the question in the context of global weather forecasts. A toy model for global weather predictions will be presented and used to identify challenges and fundamental design choices for a forecast system based on neural networks.