A conditional Generative Adversarial network model for the Weather4Cast 2024 Challenge
This work addresses rainfall forecasting for meteorology, but it is incremental as it applies existing deep learning methods to a specific competition dataset.
The study tackled rainfall prediction by using a conditional GAN to transform forecasted radiance images into cumulative rainfall values over 4 hours, achieving a CRPS score of approximately 7.5 and placing first in the Weather4Cast 2024 competition.
This study explores the application of deep learning for rainfall prediction, leveraging the Spinning Enhanced Visible and Infrared Imager (SEVIRI) High rate information transmission (HRIT) data as input and the Operational Program on the Exchange of weather RAdar information (OPERA) ground-radar reflectivity data as ground truth. We use the mean of 4 InfraRed frequency channels as the input. The radiance images are forecasted up to 4 hours into the future using a dense optical flow algorithm. A conditional generative adversarial network (GAN) model is employed to transform the predicted radiance images into rainfall images which are aggregated over the 4 hour forecast period to generate cumulative rainfall values. This model scored a value of approximately 7.5 as the Continuous Ranked Probability Score (CRPS) in the Weather4Cast 2024 competition and placed 1st on the core challenge leaderboard.