Precipitation Nowcasting Using Physics Informed Discriminator Generative Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913391324430336 |
|---|---|
| author | Yin, Junzhe Meo, Cristian Roy, Ankush Cher, Zeineh Bou Wang, Yanbo Imhoff, Ruben Uijlenhoet, Remko Dauwels, Justin |
| author_facet | Yin, Junzhe Meo, Cristian Roy, Ankush Cher, Zeineh Bou Wang, Yanbo Imhoff, Ruben Uijlenhoet, Remko Dauwels, Justin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10108 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Precipitation Nowcasting Using Physics Informed Discriminator Generative Models Yin, Junzhe Meo, Cristian Roy, Ankush Cher, Zeineh Bou Wang, Yanbo Imhoff, Ruben Uijlenhoet, Remko Dauwels, Justin Machine Learning Artificial Intelligence 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. |
| title | Precipitation Nowcasting Using Physics Informed Discriminator Generative Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2406.10108 |