Exploring the Limit of Atmospheric Predictability with Machine Learning Models

Dr Greg Hakim
U of Washington
  1 May, 2pm

Abstract:

Research on atmospheric predictability has historically used physics-based models, which parameterize small-scale processes that strongly influence error growth. Global machine learning (ML) models enable a transformative new approach to predictability research since they have forecast skill comparable to physics-based models at a fraction of the computational cost, and tools to take derivatives of all components of the forecast. We use these tools to map forecast errors from long forecast lead times, when they are large relative to analysis uncertainty, backward in time to the initial condition. This approach yields a deterministic, state-dependent, estimate of the limit of predictability, and statistics on the corrections to operational analyses that may improve long-lead weather forecasts.