Preprints
https://doi.org/10.5194/egusphere-2025-3162
https://doi.org/10.5194/egusphere-2025-3162
18 Jul 2025
 | 18 Jul 2025

Assessing seasonal climate predictability using a deep learning application: NN4CAST

Víctor Galván Fraile, María Belén Rodríguez-Fonseca, Irene Polo, Marta Martín-Rey, and María N. Moreno-García

Abstract. Seasonal climate predictions are essential for climate services, being the changes in tropical sea surface temperature (SST) the most influential drivers. SST anomalies can affect the climate in remote regions through various atmospheric teleconnection mechanisms, and the persistence/evolution of those SST anomalies can give seasonal predictability to atmospheric signals. Dynamical models often struggle with biases and low signal-to-noise ratios, making statistical methods a valuable alternative. Deep learning models are currently providing accurate predictions, mainly in short range weather forecast. Nevertheless, the blackbox nature of this methodology makes necessary the identification of its explainability. In this context, we present NN4CAST (Neural Network foreCAST), a versatile Python deep learning tool designed to assess seasonal predictability. Starting from the original files, NN4CAST performs all the methodological steps, enabling researchers to rapidly explore the predictability of a target variable and identify its main drivers. This flexible framework allows for the quick testing of predictive skill from different sources of predictability, making it a valuable asset for climate services. As SST is the primary source of seasonal predictability, we illustrate the application of NN4CAST to tropical and extratropical teleconnections forced by the Pacific SSTs. We show that NN4CAST can provide skillful seasonal forecasts in regions where the atmospheric response to SST anomalies is predominantly linear, such as the tropics, as well as in remote regions where the signal is highly non-linear, like Europe. Two key examples are the prediction of SST anomalies in the tropical Atlantic region during boreal spring and precipitation anomalies over the European continent during boreal autumn. The former exemplifies a predominantly linear tropical linear ENSO-Tropical North Atlantic, whereas the latter involves a highly non-linear and non-stationary ENSO-Euro-Atlantic teleconnection. Our results demonstrates NN4CAST’s potential to determine and quantify the influence of specific drivers on a target variable, offering a useful tool for improving climate predictability assessments. NN4CAST enables the attribution of predictions to specific input features, helping to identify the relative importance of different sources of predictability over time and space. In summary, NN4CAST offers a powerful framework to better characterize and understand the complex, non-linear, and non-stationary remote climate interactions.

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 paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
Víctor Galván Fraile, María Belén Rodríguez-Fonseca, Irene Polo, Marta Martín-Rey, and María N. Moreno-García

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2025-3162', Anonymous Referee #1, 26 Aug 2025
  • RC2: 'Comment on egusphere-2025-3162', Anonymous Referee #2, 09 Sep 2025
  • RC3: 'Comment on egusphere-2025-3162', Anonymous Referee #3, 22 Sep 2025
Víctor Galván Fraile, María Belén Rodríguez-Fonseca, Irene Polo, Marta Martín-Rey, and María N. Moreno-García

Data sets

NN4CAST_manual Víctor Galván Fraile et al. https://doi.org/10.5281/zenodo.15682872

Model code and software

NN4CAST Víctor Galván Fraile https://doi.org/10.5281/zenodo.14011998

Víctor Galván Fraile, María Belén Rodríguez-Fonseca, Irene Polo, Marta Martín-Rey, and María N. Moreno-García

Viewed

Total article views: 1,874 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,776 75 23 1,874 26 22 21
  • HTML: 1,776
  • PDF: 75
  • XML: 23
  • Total: 1,874
  • Supplement: 26
  • BibTeX: 22
  • EndNote: 21
Views and downloads (calculated since 18 Jul 2025)
Cumulative views and downloads (calculated since 18 Jul 2025)

Viewed (geographical distribution)

Total article views: 1,871 (including HTML, PDF, and XML) Thereof 1,871 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Oct 2025
Download
Short summary
We present a new deep learning framework designed to assess seasonal climate predictability by identifying the key predictors that influence climate variability across different regions. This tool enhances understanding of how remote areas are connected through climate interactions and provides more accurate and explainable predictions. Our results demonstrate its potential to support more reliable and informed climate services at both regional and global scales.
Share