Non-orographic gravity wave drag dataset

Public data repository for Chantry et al. (2020) on NOGWD emulation using machine learning See paper for details on data generation. To unzip: <pre><code class="language-bash">tar -xzf 2015-01-01.h5.tgz </code></pre> Files are formatted year-month-day.h5 based on forecast start date.<br> Files contain arrays x &amp; y<br> Inputs: x(191,ntime,nspace)<br> Outputs: y(126,ntime,nspace)<br> ntime=36 (every 20 hours from 20:720 hours)<br> nspace=65440 (subsampling every 10th gridpoint of 654400 original points)<br> See paper for explanation of the 191 &amp; 126.<br> Data has not been normalised. Challenge is for a given 191 inputs, predict the 126 outputs. Training data: used 12 30-day periods in 2015.<br> Testing: 3 provided dates in 2016.<br> Validation: 3 provided dates in 2017