EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Observational Uncertainty in Deep Learning Climate Downscaling and Projections

Samuel Reyes‐Elgueta, Jose González‐Abad, Javier Diez‐Sierra, Sixto Herrera, José Manuel Gutiérrez

Earth and Space Science · 2026-06 · 13 (6)

DOI: 10.1029/2025ea004973 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Earth and Space Science, online erschienen am 11.06.2026. Verfasst von Samuel Reyes‐Elgueta und 4 weiteren Autor:innen. Die Arbeit nennt 86 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) models are increasingly used for climate downscaling, yet the impact of observational uncertainty on their performance remains poorly understood. Here we assess this effect by training ensembles of DL downscaling models using four independent gridded observational data sets over continental Spain that differ in source, methodology, and spatial coverage. Each ensemble includes multiple training realizations of the same model to capture training variability. The models are then applied to downscale global climate model temperature projections. Results show that both intra‐model (across realizations) and inter‐dataset (across observational products) variability substantially influence the downscaled climate change signal. Differences among data sets dominate this uncertainty, especially for extremes (annual 99th percentile) at regional scales, leading to warming discrepancies of up to 2.5°C. However, these discrepancies are smaller for high‐quality regional data sets built from dense observation networks and rigorous quality control, whereas global observational data sets, known to misrepresent local climate features (Bedia et al., 2013, https://doi.org/10.1016/j.gloplacha.2013.04.005 ), exert a larger impact on downscaled projections. These findings highlight that the use of well‐constructed regional data sets can substantially reduce uncertainty and improve the reliability of deep learning–based downscaling. Explicitly incorporating observational uncertainty into training and evaluation frameworks remains essential to ensure robust and credible regional climate projections.

Zitieren

APA

Reyes‐Elgueta, S., González‐Abad, J., Diez‐Sierra, J., Herrera, S., & Gutiérrez, J. M. (2026). Observational Uncertainty in Deep Learning Climate Downscaling and Projections. Earth and Space Science, 13(6). https://doi.org/10.1029/2025ea004973

Vancouver

Reyes‐Elgueta S, González‐Abad J, Diez‐Sierra J, Herrera S, Gutiérrez JM. Observational Uncertainty in Deep Learning Climate Downscaling and Projections. Earth and Space Science. 2026;13(6). doi:10.1029/2025ea004973

BibTeX
@article{ReyesElgueta2026,
  author = {Reyes‐Elgueta, Samuel and González‐Abad, Jose and Diez‐Sierra, Javier and Herrera, Sixto and Gutiérrez, José Manuel},
  title = {Observational Uncertainty in Deep Learning Climate Downscaling and Projections},
  journal = {Earth and Space Science},
  year = {2026},
  volume = {13},
  number = {6},
  doi = {10.1029/2025ea004973}
}
Kostenlos starten →