FuXi-Nowcast: Environment-conditioned deep learning for severe convection nowcasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Lei, Zhu, Zijian, Zhuang, Xiaoran, Qi, Tianyuan, Feng, Yuxuan, Zhong, Xiaohui, Li, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916044119998464
author Chen, Lei
Zhu, Zijian
Zhuang, Xiaoran
Qi, Tianyuan
Feng, Yuxuan
Zhong, Xiaohui
Li, Hao
author_facet Chen, Lei
Zhu, Zijian
Zhuang, Xiaoran
Qi, Tianyuan
Feng, Yuxuan
Zhong, Xiaohui
Li, Hao
contents Severe convection produces localized hazards that often require warnings before radar echoes fully reveal storm development. Convective initiation and the maintenance of intense convection remain challenging for radar-only nowcasting because pre-convective signals may be absent from recent radar observations and strong echoes often decay rapidly in forecasts. Here we present FuXi-Nowcast, an environment-conditioned deep learning system that combines high-resolution observations with three-dimensional atmospheric forecasts to predict composite reflectivity, precipitation, wind gusts, and surface variables up to 12 h ahead. In April--July 2024 evaluations over East China, FuXi-Nowcast outperforms operational numerical, persistence and extrapolation baselines for reflectivity and precipitation. Case studies, diagnostics, and ablation experiments suggest that atmospheric moisture information and explicit preservation of strong convective signals contribute to forecasts of convective initiation and maintenance. These results show that environmental conditioning can mitigate important failure modes of radar-only nowcasting for high-impact convective weather.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08974
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FuXi-Nowcast: Environment-conditioned deep learning for severe convection nowcasting
Chen, Lei
Zhu, Zijian
Zhuang, Xiaoran
Qi, Tianyuan
Feng, Yuxuan
Zhong, Xiaohui
Li, Hao
Atmospheric and Oceanic Physics
Machine Learning
Severe convection produces localized hazards that often require warnings before radar echoes fully reveal storm development. Convective initiation and the maintenance of intense convection remain challenging for radar-only nowcasting because pre-convective signals may be absent from recent radar observations and strong echoes often decay rapidly in forecasts. Here we present FuXi-Nowcast, an environment-conditioned deep learning system that combines high-resolution observations with three-dimensional atmospheric forecasts to predict composite reflectivity, precipitation, wind gusts, and surface variables up to 12 h ahead. In April--July 2024 evaluations over East China, FuXi-Nowcast outperforms operational numerical, persistence and extrapolation baselines for reflectivity and precipitation. Case studies, diagnostics, and ablation experiments suggest that atmospheric moisture information and explicit preservation of strong convective signals contribute to forecasts of convective initiation and maintenance. These results show that environmental conditioning can mitigate important failure modes of radar-only nowcasting for high-impact convective weather.
title FuXi-Nowcast: Environment-conditioned deep learning for severe convection nowcasting
topic Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2512.08974