SynWeather: Weather Observation Data Synthesis across Multiple Regions and Variables via a General Diffusion Transformer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Kaiyi, Gong, Junchao, Zhou, Zhiwang, Li, Zhangrui, Pu, Yuandong, Liu, Yihao, Fei, Ben, Ling, Fenghua, Zhang, Wenlong, Bai, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918202249838592
author Xu, Kaiyi
Gong, Junchao
Zhou, Zhiwang
Li, Zhangrui
Pu, Yuandong
Liu, Yihao
Fei, Ben
Ling, Fenghua
Zhang, Wenlong
Bai, Lei
author_facet Xu, Kaiyi
Gong, Junchao
Zhou, Zhiwang
Li, Zhangrui
Pu, Yuandong
Liu, Yihao
Fei, Ben
Ling, Fenghua
Zhang, Wenlong
Bai, Lei
contents With the advancement of meteorological instruments, abundant data has become available. Current approaches are typically focus on single-variable, single-region tasks and primarily rely on deterministic modeling. This limits unified synthesis across variables and regions, overlooks cross-variable complementarity and often leads to over-smoothed results. To address above challenges, we introduce SynWeather, the first dataset designed for Unified Multi-region and Multi-variable Weather Observation Data Synthesis. SynWeather covers four representative regions: the Continental United States, Europe, East Asia, and Tropical Cyclone regions, as well as provides high-resolution observations of key weather variables, including Composite Radar Reflectivity, Hourly Precipitation, Visible Light, and Microwave Brightness Temperature. In addition, we introduce SynWeatherDiff, a general and probabilistic weather synthesis model built upon the Diffusion Transformer framework to address the over-smoothed problem. Experiments on the SynWeather dataset demonstrate the effectiveness of our network compared with both task-specific and general models.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08291
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SynWeather: Weather Observation Data Synthesis across Multiple Regions and Variables via a General Diffusion Transformer
Xu, Kaiyi
Gong, Junchao
Zhou, Zhiwang
Li, Zhangrui
Pu, Yuandong
Liu, Yihao
Fei, Ben
Ling, Fenghua
Zhang, Wenlong
Bai, Lei
Computer Vision and Pattern Recognition
With the advancement of meteorological instruments, abundant data has become available. Current approaches are typically focus on single-variable, single-region tasks and primarily rely on deterministic modeling. This limits unified synthesis across variables and regions, overlooks cross-variable complementarity and often leads to over-smoothed results. To address above challenges, we introduce SynWeather, the first dataset designed for Unified Multi-region and Multi-variable Weather Observation Data Synthesis. SynWeather covers four representative regions: the Continental United States, Europe, East Asia, and Tropical Cyclone regions, as well as provides high-resolution observations of key weather variables, including Composite Radar Reflectivity, Hourly Precipitation, Visible Light, and Microwave Brightness Temperature. In addition, we introduce SynWeatherDiff, a general and probabilistic weather synthesis model built upon the Diffusion Transformer framework to address the over-smoothed problem. Experiments on the SynWeather dataset demonstrate the effectiveness of our network compared with both task-specific and general models.
title SynWeather: Weather Observation Data Synthesis across Multiple Regions and Variables via a General Diffusion Transformer
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.08291