FuXi-Nowcast: Meet the longstanding challenge of convective initiation in nowcasting

TL;DR

FuXi-Nowcast is a deep-learning system that improves the accuracy of short-term weather forecasts, especially for convective storms, by integrating multi-source data and advanced neural network architectures, outperforming existing models in key metrics.

Contribution

This paper introduces FuXi-Nowcast, a novel multi-task deep-learning framework that combines diverse observational data with atmospheric modeling to enhance convective storm nowcasting accuracy.

Findings

FuXi-Nowcast outperforms CMA-MESO 3-km model in critical success index for key weather parameters.

The system more accurately predicts timing, location, and structure of convective initiation.

Significant improvements in heavy rainfall prediction at lead times up to 12 hours.

Abstract

Accurate nowcasting of convective storms remains a major challenge for operational forecasting, particularly for convective initiation and the evolution of high-impact rainfall and strong winds. Here we present FuXi-Nowcast, a deep-learning system that jointly predicts composite radar reflectivity, surface precipitation, near-surface temperature, wind speed and wind gusts at 1-km resolution over eastern China. FuXi-Nowcast integrates multi-source observations, such as radar, surface stations and the High-Resolution Land Data Assimilation System (HRLDAS), with three-dimensional atmospheric fields from the machine-learning weather model FuXi-2.0 within a multi-task Swin-Transformer architecture. A convective signal enhancement module and distribution-aware hybrid loss functions are designed to preserve intense convective structures and mitigate the rapid intensity decay common in deep-learning nowcasts. FuXi-Nowcast surpasses the operational CMA-MESO 3-km numerical model in Critical Success Index for reflectivity, precipitation and wind gusts across thresholds and lead times up to 12 h, with the largest gains for heavy rainfall. Case studies further show that FuXi-Nowcast more accurately captures the timing, location and structure of convective initiation and subsequent evolution of convection. These results demonstrate that coupling three-dimensional machine-learning forecasts with high-resolution observations can provide multi-hazard, long-lead nowcasts that outperforms current operational systems.