SRDiff: A Cross-Modal Diffusion Model for Satellite-to-Radar Translation in Precipitation Nowcasting

Satellite-to-radar translation is a critical yet under-explored task in modern weather forecasting. While satellites provide near-global coverage and high-frequency updates, their multi-channel radiance data is difficult to interpret directly by forecasters or end-users, and not readily compatible with existing radar-based forecasting models. By converting satellite observations into radar-equivalent representations, we can (i) extend radar-like availability to regions without ground-based radar coverage, (ii) provide a more compact and operationally meaningful representation of storms, and (iii) enable the reuse of a large ecosystem of radar-based nowcasting models without retraining. Despite its importance, methods tailored for this task remain limited, and the performance of general-purpose generative models has not been systematically benchmarked. To fill this gap, we propose SRDiff, a cross-modal, sequence-aware diffusion model specifically designed for satellite-to-radar translation. SRDiff employs a Cross-Modal Conditional Adapter to align heterogeneous satellite channels with radar reflectivity, and a Diffusion Transformer backbone to capture sequential dependencies, producing stable and coherent radar predictions. Extensive experiments on the SEVIR and Sat2Rdr datasets show that SRDiff outperforms existing deterministic and diffusion-based methods on the satellite-to-radar translation task across all key metrics. As a downstream application, we integrate SRDiff with off-the-shelf radar-based nowcasting models, demonstrating three key advantages: (i) operational efficiency, since no new training is required, (ii) strong forecasting accuracy, often surpassing models trained from scratch, and (iii) practical validation that effective satellite-to-radar translation directly improves downstream now-casting. Code is available at https://github.com/42xingxing/SRDiff.