Nature Communications (Jul 2024)

A machine learning model that outperforms conventional global subseasonal forecast models

  • Lei Chen,
  • Xiaohui Zhong,
  • Hao Li,
  • Jie Wu,
  • Bo Lu,
  • Deliang Chen,
  • Shang-Ping Xie,
  • Libo Wu,
  • Qingchen Chao,
  • Chensen Lin,
  • Zixin Hu,
  • Yuan Qi

DOI
https://doi.org/10.1038/s41467-024-50714-1
Journal volume & issue
Vol. 15, no. 1
pp. 1 – 14

Abstract

Read online

Abstract Skillful subseasonal forecasts are crucial for various sectors of society but pose a grand scientific challenge. Recently, machine learning-based weather forecasting models outperform the most successful numerical weather predictions generated by the European Centre for Medium-Range Weather Forecasts (ECMWF), but have not yet surpassed conventional models at subseasonal timescales. This paper introduces FuXi Subseasonal-to-Seasonal (FuXi-S2S), a machine learning model that provides global daily mean forecasts up to 42 days, encompassing five upper-air atmospheric variables at 13 pressure levels and 11 surface variables. FuXi-S2S, trained on 72 years of daily statistics from ECMWF ERA5 reanalysis data, outperforms the ECMWF’s state-of-the-art Subseasonal-to-Seasonal model in ensemble mean and ensemble forecasts for total precipitation and outgoing longwave radiation, notably enhancing global precipitation forecast. The improved performance of FuXi-S2S can be primarily attributed to its superior capability to capture forecast uncertainty and accurately predict the Madden-Julian Oscillation (MJO), extending the skillful MJO prediction from 30 days to 36 days. Moreover, FuXi-S2S not only captures realistic teleconnections associated with the MJO but also emerges as a valuable tool for discovering precursor signals, offering researchers insights and potentially establishing a new paradigm in Earth system science research.