EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

HiResCastNet: A 3D Deep Learning Model for Probabilistic Regional High‐Resolution Subseasonal Forecasting Through Downscaling

Sofien Resifi, Elissar Al Aawar, Thang Luong, Ibrahim Hoteit

Journal of Geophysical Research: Machine Learning and Computation · 2026-12 · 3 (6)

DOI: 10.1029/2026jh001400 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Geophysical Research: Machine Learning and Computation, online erschienen am 31.10.2026. Verfasst von Sofien Resifi und 3 weiteren Autor:innen. Die Arbeit nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: King Abdullah University of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High‐resolution subseasonal forecasts, spanning two to 6 weeks, play a vital role in bridging the gap between short‐range forecasts and seasonal predictions. They provide crucial information for decision‐making in disaster and hazard preparedness, early warning systems, water resource management, and renewable energy. However, generating subseasonal forecasts at high spatial and temporal resolutions remains a significant challenge. Global subseasonal forecasting systems such as European Center for Medium‐Range Weather Forecasts (ECMWF) typically provide outputs at a coarse spatial resolution of about 31 km and a temporal resolution of 12 hr, which limits their usefulness for regional‐scale planning and impact assessments. Our three‐dimensional (3D) high‐resolution regional subseasonal forecasts are generated by dynamically downscaling the ECMWF subseasonal forecasts using the Weather Research and Forecasting (WRF) model, producing outputs at a spatial resolution of 4 km and a temporal resolution of 3 hr. Yet, the dynamical downscaling model is computationally very demanding, especially when using multiple ensemble members. To address this limitation, we introduce HiResCastNet, a data‐driven, probabilistic downscaling framework combining Swin‐transformer and a diffusion model, which serves as an efficient surrogate for the traditional downscaling system. HiResCastNet takes spatio‐temporal coarse resolution forecasts from ECMWF subseasonal system as inputs, and generates 3D high‐resolution forecasts at 4 km spatial resolution and 3‐hourly intervals. Our results suggest that HiResCastNet significantly reduces computational cost while maintaining strong agreement with WRF physical model. It reproduces the dynamical behavior across variables such as wind and temperature and handles the downscaling of multiple ensemble members efficiently, which highlights its potential for operational use.

Förderung

  • King Abdullah University of Science and Technology

Zitieren

APA

Resifi, S., Aawar, E. A., Luong, T., & Hoteit, I. (2026). HiResCastNet: A 3D Deep Learning Model for Probabilistic Regional High‐Resolution Subseasonal Forecasting Through Downscaling. Journal of Geophysical Research: Machine Learning and Computation, 3(6). https://doi.org/10.1029/2026jh001400

Vancouver

Resifi S, Aawar EA, Luong T, Hoteit I. HiResCastNet: A 3D Deep Learning Model for Probabilistic Regional High‐Resolution Subseasonal Forecasting Through Downscaling. Journal of Geophysical Research: Machine Learning and Computation. 2026;3(6). doi:10.1029/2026jh001400

BibTeX
@article{Resifi2026,
  author = {Resifi, Sofien and Aawar, Elissar Al and Luong, Thang and Hoteit, Ibrahim},
  title = {HiResCastNet: A 3D Deep Learning Model for Probabilistic Regional High‐Resolution Subseasonal Forecasting Through Downscaling},
  journal = {Journal of Geophysical Research: Machine Learning and Computation},
  year = {2026},
  volume = {3},
  number = {6},
  doi = {10.1029/2026jh001400}
}
Kostenlos starten →