Data driven approaches to un(der) resolved gravity wave momentum transport
Date:
This was the first of (hopefully) a new line of Gordon Conferences focused on the role of data-driven science and machine learning in atmosphere and oceanic science.
Abstract
Gravity waves, or buoyancy waves, so named because their restoring force is the action of gravity on a stratified fluid, present a challenge to atmospheric modeling. They play an important role in the global atmospheric circulation by transporting momentum, but their horizontal scales of 10^2 to 10^5 meters cannot be fully resolved even by the highest resolution climate prediction systems. Furthermore, many of their sources, including convection and frontogenesis, are themselves not directly represented. Their impacts must therefore be approximated, or parameterized, based on resolved flow variables. The availability of new observations has raised hopes for a data driven approach to the representation of gravity waves. I’ll present evidence that a variety of machine learning techniques, including neural nets (dense, convolutional, and encoder-decoder), random forests, and support vector machines, are able to successfully capture gravity wave momentum transport in global atmospheric models. As with other sub-grid scale paramterizations, however, there are significant challenges when it comes to calibrating schemes to work in biased climate models and ensuring that they can extrapolate to unseen conditions under global warming.