A generative adversarial network approach to (ensemble) weather prediction

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 h over Europe. The proposed models are trained on 4 years of ERA5 reanalysis data from 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. (C) 2021 Elsevier Ltd. All rights reserved.

Automated summary

Using conditional deep convolutional generative adversarial networks, the study successfully predicts geopotential height and two-meter temperature over Europe, but fails to accurately predict total precipitation. The use of Monte-Carlo dropout helps improve the forecasting model's skill by quantifying uncertainty in current weather forecasts.