CastDiffuser: Cascaded latent diffusion framework for high-resolution precipitation nowcasting via multi source fusion

Precipitation nowcasting is critical for meteorological disaster warning, water resource management, and severe rainfall prediction, directly impacting public safety and daily operations. Existing methods based on discriminative modeling tend to produce ambiguous extrapolation maps. While generative models have improved perceptual metrics, they still suffer from limited prediction accuracy (e.g., skills scores such as Critical Success Index (CSI) and Fractions Skill Score (FSS)), high computational costs, and inadequate convective initiation prediction-with the latter stemming from constraints of single-source data. To address these challenges, we propose CastDiffuser, a cascaded latent diffusion framework for high-resolution and high-precision precipitation nowcasting. The framework performs cascaded modeling in the latent space and leverages complementary satellite and radar data, enabling both enhanced predictive accuracy and reduced computational cost. Specifically, CastDiffuser downscales and reconstructs high-resolution radar by variational autocoders. Then we utilize a spatio-temporal translator (ST-Translator) to model the deterministic components of precipitation evolution. Subsequently, a satellite-guided diffusion model is introduced to refine these deterministic features, which are then used to generate high-resolution radar predictions. Experiments on Jiangsu provincial meteorological datasets show CastDiffuser outperforms state-of-the-art methods in prediction accuracy and fine-detail preservation, particularly for heavy rainfall and convective initiation events. • We propose CastDiffuser, a Cascaded Latent Diffusion Framework thatintegrates radar and satellite data in latent space for precipitation forecasting.By modeling in a low-dimensional latent space with a cascaded design, CastDiffuser achieves superior spatio-temporal prediction accuracy while significantly reducing the computational cost of high-resolution forecasting. • We design the Spatio-Temporal Translator composed of hierarchical ST-Inception modules for robust multi-scale feature extraction. This module provides stable and structured representations for subsequent diffusion learning, thereby addressing the issue of unstable input features and improving forecast accuracy. • We introduce FsrFormer, a multi-source fusion denoising network acting as a spatial refinement module. FsrFormer adaptively modulates the influence of satellite-derived features during the diffusion process across different time steps, facilitating efficient and dynamic fusion of multi-source information. • Experimental results on real-world datasets show that the proposed CastDiffuser significantly improves the prediction performance of heavy precipitation and maintains this accuracy over a longer forecast period, especially in the convective incipient prediction task.