Data-driven Precipitation Nowcasting Using Satellite Imagery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912158667767808 |
|---|---|
| author | Park, Young-Jae Kim, Doyi Seo, Minseok Jeon, Hae-Gon Choi, Yeji |
| author_facet | Park, Young-Jae Kim, Doyi Seo, Minseok Jeon, Hae-Gon Choi, Yeji |
| contents | Accurate precipitation forecasting is crucial for early warnings of disasters, such as floods and landslides. Traditional forecasts rely on ground-based radar systems, which are space-constrained and have high maintenance costs. Consequently, most developing countries depend on a global numerical model with low resolution, instead of operating their own radar systems. To mitigate this gap, we propose the Neural Precipitation Model (NPM), which uses global-scale geostationary satellite imagery. NPM predicts precipitation for up to six hours, with an update every hour. We take three key channels to discriminate rain clouds as input: infrared radiation (at a wavelength of 10.5 $μm$), upper- (6.3 $μm$), and lower- (7.3 $μm$) level water vapor channels. Additionally, NPM introduces positional encoders to capture seasonal and temporal patterns, accounting for variations in precipitation. Our experimental results demonstrate that NPM can predict rainfall in real-time with a resolution of 2 km. The code and dataset are available at https://github.com/seominseok0429/Data-driven-Precipitation-Nowcasting-Using-Satellite-Imagery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11480 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data-driven Precipitation Nowcasting Using Satellite Imagery Park, Young-Jae Kim, Doyi Seo, Minseok Jeon, Hae-Gon Choi, Yeji Computer Vision and Pattern Recognition Image and Video Processing Accurate precipitation forecasting is crucial for early warnings of disasters, such as floods and landslides. Traditional forecasts rely on ground-based radar systems, which are space-constrained and have high maintenance costs. Consequently, most developing countries depend on a global numerical model with low resolution, instead of operating their own radar systems. To mitigate this gap, we propose the Neural Precipitation Model (NPM), which uses global-scale geostationary satellite imagery. NPM predicts precipitation for up to six hours, with an update every hour. We take three key channels to discriminate rain clouds as input: infrared radiation (at a wavelength of 10.5 $μm$), upper- (6.3 $μm$), and lower- (7.3 $μm$) level water vapor channels. Additionally, NPM introduces positional encoders to capture seasonal and temporal patterns, accounting for variations in precipitation. Our experimental results demonstrate that NPM can predict rainfall in real-time with a resolution of 2 km. The code and dataset are available at https://github.com/seominseok0429/Data-driven-Precipitation-Nowcasting-Using-Satellite-Imagery. |
| title | Data-driven Precipitation Nowcasting Using Satellite Imagery |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2412.11480 |