A generative adversarial network approach to (ensemble) weather prediction

TL;DR

This paper introduces a deep learning approach using generative adversarial networks to predict key weather variables over Europe, demonstrating promising results for some parameters and developing an efficient ensemble forecasting system.

Contribution

It presents a novel GAN-based model for weather prediction and integrates Monte-Carlo dropout to quantify forecast uncertainty, advancing data-driven meteorological forecasting methods.

Findings

Good agreement for geopotential height and temperature predictions

Poor performance in total precipitation forecasting

Ensemble system improves forecast skill and uncertainty quantification

Abstract

We use a conditional deep convolutional generative adversarial network to predict the geopotential height of the 500 hPa pressure level, the two-meter temperature and the total precipitation for the next 24 hours over Europe. The proposed models are trained on 4 years of ERA5 reanalysis data from 2015-2018 with the goal to predict the associated meteorological fields in 2019. The forecasts show a good qualitative and quantitative agreement with the true reanalysis data for the geopotential height and two-meter temperature, while failing for total precipitation, thus indicating that weather forecasts based on data alone may be possible for specific meteorological parameters. We further use Monte-Carlo dropout to develop an ensemble weather prediction system based purely on deep learning strategies, which is computationally cheap and further improves the skill of the forecasting model, by allowing to quantify the uncertainty in the current weather forecast as learned by the model.