Precipitation Nowcasting Using Physics Informed Discriminator Generative Models
J. Yin (TU Delft - Electrical Engineering, Mathematics and Computer Science)
C. Meo (TU Delft - Signal Processing Systems)
A. Roy (TU Delft - Signal Processing Systems)
Zeineh Bou Cher (Student TU Delft)
Mircea Lică (Student TU Delft)
Y. Wang (TU Delft - Signal Processing Systems)
R. O. Imhoff (Deltares)
R. Uijlenhoet (TU Delft - Water Resources)
J.H.G. Dauwels (TU Delft - Signal Processing Systems)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Nowcasting leverages real-time atmospheric conditions to forecast weather over short periods. State-of-the-art models, including PySTEPS, encounter difficulties in accurately forecasting extreme weather events because of their unpredictable distribution patterns. In this study, we design a physics-informed neural network to perform precipitation nowcasting using the precipitation and meteorological data from the Royal Netherlands Meteorological Institute (KNMI). This model draws inspiration from the novel Physics-Informed Discriminator GAN (PID-GAN) formulation, directly integrating physics-based supervision within the adversarial learning framework. The proposed model adopts a GAN structure, featuring a Vector Quantization Generative Adversarial Network (VQ-GAN) and a Transformer as the generator, with a temporal discriminator serving as the discriminator. Our findings demonstrate that the PID-GAN model outperforms numerical and SOTA deep generative models in terms of precipitation nowcasting downstream metrics.