Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 13, issue 5
Articles | Volume 13, issue 5
https://doi.org/10.5194/gmd-13-2185-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-13-2185-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 13, issue 5
Development and technical paper
 | 
08 May 2020
Development and technical paper |  | 08 May 2020

Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations: general algorithms and Lorenz 96 case study (v1.0)

Stephan Rasp

Viewed

Total article views: 6,049 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
4,036 1,868 145 6,049 209 227
  • HTML: 4,036
  • PDF: 1,868
  • XML: 145
  • Total: 6,049
  • BibTeX: 209
  • EndNote: 227
Views and downloads (calculated since 07 Jan 2020)
Cumulative views and downloads (calculated since 07 Jan 2020)

Viewed (geographical distribution)

Total article views: 6,049 (including HTML, PDF, and XML) Thereof 5,603 with geography defined and 446 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Nov 2025
Download
Short summary
Subgrid parameterizations are largely responsible for uncertainties in climate models. Recently, several studies tried to improve the representation of subgrid processes by learning parameterization directly from high-resolution modeling data. In this paper, the current state of the art of this research direction is summarized, and an algorithm is proposed to combat major problems with existing approaches, namely instabilities and biases.
Read more
Share