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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: He, Xuming, Zhou, Zhiwang, Zhang, Wenlong, Zhao, Xiangyu, Chen, Hao, Chen, Shiqi, Bai, Lei
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909383492894720
author He, Xuming
Zhou, Zhiwang
Zhang, Wenlong
Zhao, Xiangyu
Chen, Hao
Chen, Shiqi
Bai, Lei
author_facet He, Xuming
Zhou, Zhiwang
Zhang, Wenlong
Zhao, Xiangyu
Chen, Hao
Chen, Shiqi
Bai, Lei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06714
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations
He, Xuming
Zhou, Zhiwang
Zhang, Wenlong
Zhao, Xiangyu
Chen, Hao
Chen, Shiqi
Bai, Lei
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
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.
title DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.06714