通过雷达观测与基础模型先验的谱融合拓展临近降水预报视界

摘要

降水临近预报对灾害防治和航空安全至关重要。然而，纯雷达模型常因缺乏大尺度大气环境信息，导致预报性能随预见期延长而下降。虽然融合气象基础模型预测的变量可提供潜在解决方案，但现有架构难以弥合雷达图像与气象数据间显著的表示异质性。为此，我们提出PW-FouCast——一种新颖的频域融合框架，该框架在傅里叶主干网络中利用盘古气象预报作为频谱先验。我们的架构包含三大创新：(i) 盘古气象引导的频域调制技术，使频谱幅相与气象先验对齐；(ii) 频率记忆模块，用于修正相位差异并保持时序演化规律；(iii) 逆向频率注意力机制，重建频谱滤波中通常丢失的高频细节。在SEVIR和MeteoNet基准上的大量实验表明，PW-FouCast实现了最先进的性能，在保持结构保真度的同时有效延长了可靠预报时效。代码已开源：https://github.com/Onemissed/PW-FouCast。

English

Precipitation nowcasting is critical for disaster mitigation and aviation safety. However, radar-only models frequently suffer from a lack of large-scale atmospheric context, leading to performance degradation at longer lead times. While integrating meteorological variables predicted by weather foundation models offers a potential remedy, existing architectures fail to reconcile the profound representational heterogeneities between radar imagery and meteorological data. To bridge this gap, we propose PW-FouCast, a novel frequency-domain fusion framework that leverages Pangu-Weather forecasts as spectral priors within a Fourier-based backbone. Our architecture introduces three key innovations: (i) Pangu-Weather-guided Frequency Modulation to align spectral magnitudes and phases with meteorological priors; (ii) Frequency Memory to correct phase discrepancies and preserve temporal evolution; and (iii) Inverted Frequency Attention to reconstruct high-frequency details typically lost in spectral filtering. Extensive experiments on the SEVIR and MeteoNet benchmarks demonstrate that PW-FouCast achieves state-of-the-art performance, effectively extending the reliable forecast horizon while maintaining structural fidelity. Our code is available at https://github.com/Onemissed/PW-FouCast.

通过雷达观测与基础模型先验的谱融合拓展临近降水预报视界

Extending Precipitation Nowcasting Horizons via Spectral Fusion of Radar Observations and Foundation Model Priors

摘要

Support