Work

SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale

Year: 2024

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2406.16955

Authors: Stock, Jason, Hilburn, Kyle, Ebert-Uphoff, Imme, Anderson, Charles

Language: English

Topic: Meteorological Phenomena and Simulations

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: green

Funders: National Science Foundation, University at Albany

Award: AI Institute: Artificial Intelligence for Environmental Sciences (AI2ES)

OpenAlex ID: W4400064500

Cites:

Cited by: 1

Related to: 10