Using Deep Learning to Identify Initial Error Sensitivity for Interpretable ENSO Forecasts

Kinya Toride; Matthew Newman; Andrew Hoell; Antonietta Capotondi; Jakob Schlör; Dillon Amaya

doi:https://doi.org/10.5194/egusphere-egu25-14642

[Back] [Session NP2.2]

EGU25-14642, updated on 15 Mar 2025

https://doi.org/10.5194/egusphere-egu25-14642

EGU General Assembly 2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Using Deep Learning to Identify Initial Error Sensitivity for Interpretable ENSO Forecasts

Kinya Toride

^1,2, Matthew Newman

², Andrew Hoell², Antonietta Capotondi

^1,2, Jakob Schlör

³, and Dillon Amaya²

Kinya Toride et al.

¹CIRES, University of Colorado Boulder, Boulder, United States of America
²NOAA Physical Sciences Laboratory, Boulder, United States of America
³European Centre for Medium Range Weather Forecasts (ECMWF), Reading, UK

How to cite: Toride, K., Newman, M., Hoell, A., Capotondi, A., Schlör, J., and Amaya, D.: Using Deep Learning to Identify Initial Error Sensitivity for Interpretable ENSO Forecasts, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-14642, https://doi.org/10.5194/egusphere-egu25-14642, 2025.

This abstract has been withdrawn on 02 Apr 2025.