DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations

TL;DR

DiffSR is a novel diffusion-based approach for synthesizing radar reflectivity from satellite data, effectively capturing high-frequency details and high-value regions, surpassing previous reconstruction methods.

Contribution

The paper introduces a two-stage diffusion model that improves radar data synthesis from satellite observations, overcoming over-smoothing issues of prior methods.

Findings

Achieves state-of-the-art synthesis quality

Generates high-frequency details effectively

Accurately reproduces high-value observation areas

Abstract

Weather radar data synthesis can fill in data for areas where ground observations are missing. Existing methods often employ reconstruction-based approaches with MSE loss to reconstruct radar data from satellite observation. However, such methods lead to over-smoothing, which hinders the generation of high-frequency details or high-value observation areas associated with convective weather. To address this issue, we propose a two-stage diffusion-based method called DiffSR. We first pre-train a reconstruction model on global-scale data to obtain radar estimation and then synthesize radar reflectivity by combining radar estimation results with satellite data as conditions for the diffusion model. Extensive experiments show that our method achieves state-of-the-art (SOTA) results, demonstrating the ability to generate high-frequency details and high-value areas.