Papers for

meteorological services

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Neural SDEs improve continuous probabilistic weather forecasts up to five days

SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEs

Abstract: Existing machine learning weather forecasting models typically generate forecasts through autoregressive rollouts at a fixed temporal resolution. While highly efficient for long-range prediction, this formulation can suffer from severe error accumulation when used with shorter time steps and does not explicitly encode the locality and temporal continuity of atmospheric dynamics. To address these limitations, we introduce **SDECast**, a Neural Stochastic Differential Equation (SDE) framework for continuous-time probabilistic weather forecasting. SDECast extends SDE Matching to learn stochastic dynamics directly in physical space, without requiring repeated SDE simulation during training. On a simulated geophysical flow, we show that SDECast recovers meaningful drift dynamics and faithfully reproduces the underlying continuous-time behavior. We then demonstrate its scalability to global weather forecasting at hourly resolution, where SDECast produces skillful probabilistic forecasts for lead times of up to five days.

Fri 2 OctMachine Learning

The gist

Weather forecasting models often predict the future at fixed time steps, which can cause errors when making forecasts at shorter intervals. The authors introduce SDECast, a new method that models weather changes continuously over time using special math called Neural Stochastic Differential Equations. This approach helps capture the smooth and random nature of weather better than previous models. Tests on simulated data and real global weather show that SDECast can make accurate probabilistic predictions up to five days ahead.

Open → 2610.03313v1