Machine Learning Emulation of Gravity Wave Drag in Numerical Weather Forecasting

Abstract

We assess the value of machine learning as an accelerator for the parameterization schemes of operational weather forecasting systems, specifically the parameterization of nonorographic gravity wave drag. Emulators of this scheme can be trained to produce stable and accurate results up to seasonal forecasting timescales. Generally, networks that are more complex produce emulators that are more accurate. By training on an increased complexity version of the existing parameterization scheme, we build emulators that produce more accurate forecasts. For medium range forecasting, we have found evidence that our emulators are more accurate than the version of the parametrization scheme that is used for operational predictions. Using the current operational CPU hardware, our emulators have a similar computational cost to the existing scheme, but are heavily limited by data movement. On GPU hardware, our emulators perform 10 times faster than the existing scheme on a CPU.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jul 01, 2021
Source ID
10.1029/2021ms002477

Entities

People

  • Inna Polichtchouk
  • Matthew Chantry
  • Peter Dueben
  • Sam Hatfield
  • Tim Palmer

Organizations

  • European Centre for Medium-Range Weather Forecasts
  • European Research Council
  • European Union Agency for Cybersecurity
  • Office of Naval Research Global
  • Royal Society
  • University of Oxford

Tags

Fields of Study

  • Computer science

Readers

  • Ocean-Atmosphere Mesoscale Modeling, Data Assimilation, and Flux Boundary Layers
  • Parallel and Distributed Computing.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks