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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

An autoencoder is used to compress and then reconstruct three-dimensionalstratified turbulence data in order to better understand fluid dynamics bystudying the errors in the reconstruction. The original single data set isresolved on approximately $6.9\times10^{10}$ grid points, and 15 fluidvariables in three spatial dimensions are used, for a total of about $10^{12}$input quantities in three dimensions. The objective is to understand which ofthe input variables contains the most relevant information about the localturbulence regimes in stably stratified turbulence (SST). This is accomplishedby observing flow features that appear in one input variable but then `bleedover' to multiple output variables. The bleed over is shown to be robust withrespect to the number of layers in the autoencoder. In this proof of concept,the errors in the reconstruction include information about the spatialvariation of vertical velocity in most of the components of the reconstructedrate-of-strain tensor and density gradient, which suggests that verticalvelocity is an important marker for turbulence features of interest in SST.This result is consistent with what fluid dynamicists already understand aboutSST and, therefore, suggests an approach to understanding turbulence based onmore detailed analyses of the reconstruction on errors in an autoencodingalgorithm.

Unsupervised Machine Learning to Teach Fluid Dynamicists to Think in 15 Dimensions