Subseasonal Forecasting and MJO Teleconnections in Machine Learning Weather Prediction Models

Peings, Yannick, Dong, Cameron, Mahesh, Ankur, Pritchard, Michael, Collins, William ORCID: https://orcid.org/0000-0002-4463-9848 and Magnusdottir, Gudrun (2026) Subseasonal Forecasting and MJO Teleconnections in Machine Learning Weather Prediction Models. Journal of Geophysical Research: Atmospheres, 131 (3). ISSN 2169-897X

Full text not available from this repository. (Request a copy)

Abstract

In recent years, machine-learning (ML) models trained on reanalysis data have rivaled physics-based forecast models in terms of performance skill for global weather forecasting. With increased rollout stability, the question of how these models perform for subseasonal to seasonal (S2S, week 3–8) forecasting has emerged. In this study we run a large set of subseasonal hindcasts over 2004–2023 to evaluate two ML weather forecast models at the S2S time scale, SFNO-HENS (Nvidia, fully ML) and NeuralGCM (Google Research, hybrid). Corresponding hindcasts from the European Centre for Medium-Range Weather Forecasts (ECMWF) are used as a baseline for comparison to a physics-based model. Because our focus is on predicting moisture transport over the Western United States between October and March, we evaluate the models' prediction skill for the Madden-Julian Oscillation (MJO) and its associated teleconnections in the North Pacific. We find that both ML models are competitive with the ECWMF model, with comparable skill in predicting the North Pacific large-scale circulation and the MJO at week 3 and beyond. Even though overall the mid-latitude subseasonal prediction skill remains low, the ML models exhibit interesting behavior such as a realistic propagation of the MJO across the Maritime Continent and realistic teleconnections. A SFNO-HENS sensitivity experiment with altered initial conditions in the tropics demonstrates the stability of the model, and it illustrates the capability of ML models to represent important physical processes of the atmosphere at the S2S time scale.

Item Type:	Article
Additional Information:	Data Availability Statement: The Nvidia SFNO‐HENS model version used in this study is openly available at Mahesh, Collins, Bonev, Brenowitz, Cohen, Harrington, et al. (2025). The Google NeuralGCM model can be downloaded from https://github.com/neuralgcm/neuralgcm. S2S hindcasts from ECMWF are available at https://apps.ecmwf.int/datasets/data/s2s, and the ERA5 reanalysis at Hersbach et al. (2023). The hindcast data used in this study is too large to be shared on an open research repository but they are available upon request to the main author.
Uncontrolled Keywords:	atmospheric dynamics,machine learning,madden-julian oscillation,north pacific,southwest us,subseasonal forecasting,geophysics,atmospheric science,space and planetary science,earth and planetary sciences (miscellaneous) ,/dk/atira/pure/subjectarea/asjc/1900/1908
Faculty \ School:	Faculty of Science > School of Environmental Sciences
Related URLs:	https://www.scopus.com/pages/publication...
Depositing User:	LivePure Connector
Date Deposited:	07 Jul 2026 15:37
Last Modified:	12 Jul 2026 05:38
URI:	https://ueaeprints.uea.ac.uk/id/eprint/103772
DOI:	10.1029/2025JD044910

Actions (login required)

View Item