SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914852058955776 |
|---|---|
| author | Stock, Jason Hilburn, Kyle Ebert-Uphoff, Imme Anderson, Charles |
| author_facet | Stock, Jason Hilburn, Kyle Ebert-Uphoff, Imme Anderson, Charles |
| contents | We introduce a transformer-based neural network to generate high-resolution (3km) synthetic radar reflectivity fields at scale from geostationary satellite imagery. This work aims to enhance short-term convective-scale forecasts of high-impact weather events and aid in data assimilation for numerical weather prediction over the United States. Compared to convolutional approaches, which have limited receptive fields, our results show improved sharpness and higher accuracy across various composite reflectivity thresholds. Additional case studies over specific atmospheric phenomena support our quantitative findings, while a novel attribution method is introduced to guide domain experts in understanding model outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16955 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale Stock, Jason Hilburn, Kyle Ebert-Uphoff, Imme Anderson, Charles Signal Processing Computer Vision and Pattern Recognition Machine Learning We introduce a transformer-based neural network to generate high-resolution (3km) synthetic radar reflectivity fields at scale from geostationary satellite imagery. This work aims to enhance short-term convective-scale forecasts of high-impact weather events and aid in data assimilation for numerical weather prediction over the United States. Compared to convolutional approaches, which have limited receptive fields, our results show improved sharpness and higher accuracy across various composite reflectivity thresholds. Additional case studies over specific atmospheric phenomena support our quantitative findings, while a novel attribution method is introduced to guide domain experts in understanding model outputs. |
| title | SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale |
| topic | Signal Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.16955 |