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

TL;DR

This paper presents SRViT, a transformer-based neural network that generates high-resolution radar reflectivity fields from satellite images, improving weather forecasting accuracy and interpretability over traditional convolutional methods.

Contribution

Introduction of SRViT, a novel transformer-based model for satellite-to-radar reflectivity prediction, enhancing resolution, accuracy, and interpretability in weather forecasting.

Findings

Improved sharpness and accuracy over convolutional models.

Effective in predicting convective-scale weather phenomena.

Provides a novel attribution method for model interpretability.

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.