GraphCast : fast and more accurate weather prediction
<p><em>Weather prediction is one of the most challenging yet essential task, multitude of algorithms ranging from pure Auto-regressive architecture to pure GNN based architecture were formulated, algorithms like FourCastNet provided a deep insight into how the complex weather conditions could be modelled.</em></p>
<p>Adding on to that, very recently <a href="https://www.linkedin.com/company/googledeepmind/" rel="noopener ugc nofollow" target="_blank">Google DeepMind</a> came up with GraphCast, a GNN based encoder-process-decoder architecture that not only is able to perform high resolution predictions but also in significantly less time.<br />
claim : 10 days prediction in 1 min with 0.25 degree resolution on T4 GPU. (roughly 28sq km).</p>
<p><a href="https://medium.com/@rsiddhant73/graphcast-fast-and-more-accurate-weather-prediction-%EF%B8%8F-a567a6a72b67"><strong>Website</strong></a></p>