Preprints
https://doi.org/10.5194/npg-2024-24
https://doi.org/10.5194/npg-2024-24
20 Nov 2024
 | 20 Nov 2024
Status: this preprint is currently under review for the journal NPG.

Explaining the high skill of Reservoir Computing methods in El Niño prediction

Francesco Guardamagna, Claudia Wieners, and Henk Dijkstra

Abstract. Accurate prediction of the extreme phases of the El Niño Southern Oscillation (ENSO) is important to mitigate the socioeconomic impacts of this phenomenon. It has long been thought that prediction skill was limited to a 6 months lead time. However, Machine Learning methods have shown to have skill at lead times up to 21 months. In this paper we aim to explain for one class of such methods, i.e. Reservoir Computers (RCs), the origin of this high skill. Using a Conditional Nonlinear Optimal Perturbation (CNOP) approach, we compare the initial error propagation in a deterministic Zebiak-Cane (ZC) ENSO model and that in an RC trained on synthetic observations derived from a stochastic ZC model. Optimal initial perturbations at long lead times in the RC involve both sea surface temperature and thermocline anomalies which leads to a decreased error propagation compared to the ZC model, where mainly thermocline anomalies dominate the optimal initial perturbations. This reduced error propagation allows the RC to provide a higher skill at long lead times than the deterministic ZC model.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Francesco Guardamagna, Claudia Wieners, and Henk Dijkstra

Status: open (until 15 Jan 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on npg-2024-24', Paul Pukite, 23 Nov 2024 reply
Francesco Guardamagna, Claudia Wieners, and Henk Dijkstra
Francesco Guardamagna, Claudia Wieners, and Henk Dijkstra

Viewed

Total article views: 143 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
106 28 9 143 2 2
  • HTML: 106
  • PDF: 28
  • XML: 9
  • Total: 143
  • BibTeX: 2
  • EndNote: 2
Views and downloads (calculated since 20 Nov 2024)
Cumulative views and downloads (calculated since 20 Nov 2024)

Viewed (geographical distribution)

Total article views: 143 (including HTML, PDF, and XML) Thereof 143 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 09 Dec 2024
Download
Short summary
Artificial intelligence (AI) has recently shown promising results in ENSO (El Niño Southern Oscillation) forecasting, outperforming traditional models. Yet, AI models deliver accurate predictions without showing the underlying mechanisms. Our study examines a specific AI model, the Reservoir Computer (RC). Our results show that the RC is less sensitive to initial perturbations than the traditional Zebiak and Cane (ZC) model. This reduced sensitivity can explain the RC's superior skills.