Skip to main content
Search

# Machine learning weather forecasting

2 related articles

Subscribe to updates
  1. arXiv

    GraphCast takes over only ensemble perturbations: a month of real-observation cycling keeps background errors at least level with a physics model

    Placing the machine-learning weather model GraphCast inside a real data-assimilation cycle, with the mean still supplied by the physics-based MPAS model and GraphCast evolving only ensemble perturbations, gives ensemble spread and covariance structure comparable to an all-physics baseline over one month; the EnVar background RMSE against GFS analyses is consistently lower below model level 40, while degradation appears near the model top from interpolation and extrapolation.

    Simon Toedtli（First author）
    GraphCastData AssimilationCovariance EstimationMachine learning weather forecasting
  2. arXiv

    SoftSEEPS relaxes the SEEPS score into a differentiable loss, letting precipitation models optimize dry/light/heavy categories directly, with SEEPS dropping by up to about 0.1 at no resolvable RMSE cost

    The authors introduce SoftSEEPS, a sigmoid relaxation of the SEEPS dry/light/heavy categorical score that is differentiable and usable directly as a training loss; training a convolutional decoder on the latent space of a frozen ArchesWeather-M backbone for IMERG daily precipitation, validation discrete SEEPS falls from 0.481 with MSE only to 0.375 with SoftSEEPS only, and to 0.381 under a joint objective while RMSE rises only from 5.316 to 5.334.

    Jost Arndt（First author）
    SoftSEEPSIMERGDecoderPrecipitation ForecastingSEEPSMachine learning weather forecasting

You’re all caught up