Articles | Volume 28, issue 3
Nonlin. Processes Geophys., 28, 423–443, 2021
https://doi.org/10.5194/npg-28-423-2021
Nonlin. Processes Geophys., 28, 423–443, 2021
https://doi.org/10.5194/npg-28-423-2021

Research article 10 Sep 2021

Research article | 10 Sep 2021

Enhancing geophysical flow machine learning performance via scale separation

Davide Faranda et al.

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Davide Faranda on behalf of the Authors (19 Jan 2021)  Author's response    Manuscript
ED: Referee Nomination & Report Request started (15 Feb 2021) by Amit Apte
RR by Anonymous Referee #3 (29 Mar 2021)
RR by Matthew Levine (26 Apr 2021)
ED: Publish subject to minor revisions (review by editor) (21 Jun 2021) by Amit Apte
AR by Davide Faranda on behalf of the Authors (22 Jun 2021)  Author's response    Author's tracked changes    Manuscript
ED: Publish as is (13 Jul 2021) by Amit Apte

Post-review adjustments

AA: Author's adjustment | EA: Editor approval
AA by Davide Faranda on behalf of the Authors (01 Sep 2021)   Author's adjustment   Manuscript
EA: Adjustments approved (08 Sep 2021) by Amit Apte
Download
Short summary
Machine learning approaches are spreading rapidly in climate sciences. They are of great help in many practical situations where using the underlying equations is difficult because of the limitation in computational power. Here we use a systematic approach to investigate the limitations of the popular echo state network algorithms used to forecast the long-term behaviour of chaotic systems, such as the weather. Our results show that noise and intermittency greatly affect the performances.