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

TL;DR

This paper introduces a stochastic variational deep neural network with learned priors for precipitation nowcasting, outperforming standard models in producing clearer, longer-range weather forecasts from radar data.

Contribution

It presents a novel stochastic variational frame predictor with learned priors, improving precipitation nowcasting accuracy and clarity over traditional convolutional LSTM models.

Findings

The proposed model yields more accurate forecasts with less blur.

It maintains structural similarity over 2.5 hours of lead time.

Case studies demonstrate meaningful and sharp precipitation predictions.

Abstract

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