English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Two distinct features of anthropogenic climate change, warming in thetropical upper troposphere and warming at the Arctic surface, have competingeffects on the mid-latitude jet stream's latitudinal position, often referredto as a "tug-of-war". Studies that investigate the jet's response to thesethermal forcings show that it is sensitive to model type, season, initialatmospheric conditions, and the shape and magnitude of the forcing. Much ofthis past work focuses on studying a simulation's response to externalmanipulation. In contrast, we explore the potential to train a convolutionalneural network (CNN) on internal variability alone and then use it to examinepossible nonlinear responses of the jet to tropospheric thermal forcing thatmore closely resemble anthropogenic climate change. Our approach leverages theidea behind the fluctuation-dissipation theorem, which relates the internalvariability of a system to its forced response but so far has been only used toquantify linear responses. We train a CNN on data from a long control run ofthe CESM dry dynamical core and show that it is able to skillfully predict thenonlinear response of the jet to sustained external forcing. The trained CNNprovides a quick method for exploring the jet stream sensitivity to a widerange of tropospheric temperature tendencies and, considering that this methodcan likely be applied to any model with a long control run, could lend itselfuseful for early stage experiment design.

Using Neural Networks to Learn the Jet Stream Forced Response from Natural Variability