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

Abstract

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.

Figures (7)

• Figure 1: Qualitative comparison of predicted radar reflectivity across unimodal and multimodal methods.
• Figure 2: Overall architecture of our proposed PW-FouCast.
• Figure 3: Radar field reconstruction after integrating the amplit-ude of observations with the phase of meteorological variables.
• Figure 4: Impact of memory slots ($S$) and loss weight ($\lambda$) on model performance (MAE).
• Figure 5: Long-term sequence predictive performance on the SEVIR datasets.