Precipitation Nowcasting Using Physics Informed Discriminator Generative Models

Conference Paper (2024)
Author(s)

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)

Research Group
Water Resources
DOI related publication
https://doi.org/10.23919/EUSIPCO63174.2024.10715141
More Info
expand_more
Publication Year
2024
Language
English
Research Group
Water Resources
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. @en
Pages (from-to)
1967-1971
ISBN (electronic)
9789464593617
Reuse Rights

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.

Files

Precipitation_Nowcasting_Using... (pdf)
(pdf | 1.52 Mb)
- Embargo expired in 23-04-2025
License info not available