Precipitation Nowcasting Using Physics Informed Discriminator Generative Models
This work addresses the challenge of unpredictable extreme weather forecasting for meteorologists, representing an incremental improvement by integrating physics-based supervision into an existing adversarial framework.
The study tackled the problem of accurately forecasting extreme weather events in precipitation nowcasting by designing a physics-informed neural network, which outperformed numerical and state-of-the-art deep generative models in downstream metrics.
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.