ML@Hereon Episode 29 ' Why does it always rain on me?'

On Tuesday, June 15 at 3 PM (GMT+2), Caroline Arnold from DKRZ will present recent developments in precipitation nowcasting. High-resolution precipitation nowcasting, with a lead time of up to two
hours is relevant for many weather-dependent real world decisions such as those concerning commercial aviation, power utilities, and transportation services. Accurate nowcasts can provide a timely warning for extreme flooding and storms and can help in minimizing the loss of life and property. In this episode of the ML seminar, we will present a paper that proposes a deep generative model to forecast precipitation from radar images [1]. Ravuri et al. present a model that provides realistic and spatio-temporally consistent predictions over domains of up to 1536 km x 1280 km for lead times of 5 - 90 minutes.

The generative model has been shown to be skillful at probabilistic forecasting. It is evaluated qualitatively by human experts from the UK Met Office, and is found to be accurate and useful for actual operational application. We will also briefly cover existing approaches to precipitation nowcasting [2].

[1] Ravuri et al, Skillful Precipitation Nowcasting using Deep

[2] Prudden et al, A review of radar-based nowcasting of precipitation