Precipitation nowcasting using a stochastic variational frame predictor with learned prior distribution

We propose the use of a stochastic variational frame prediction deep neural\nnetwork with a learned prior distribution trained on two-dimensional rain radar\nreflectivity maps for precipitation nowcasting with lead times of up to 2 1/2\nhours. We present a comparison to a standard convolutional LSTM network and\nassess the evolution of the structural similarity index for both methods. Case\nstudies are presented that illustrate that the novel methodology can yield\nmeaningful forecasts without excessive blur for the time horizons of interest.\n