Using an advanced form of deep learning, researchers created a computer system that learned how to accurately predict extreme weather events, like heat waves, up to five days in advance using minimal information about current weather conditions. Ironically, the self-learning ‘capsule neural network’ uses a method reminiscent of ‘analog’ weather forecasting, which was made obsolete by computers in the 1950s.
Deep learning accurately forecasts heat waves, cold spells: Capsule neural network predicts extreme weather with WWII-era analog forecasts
