.png){kind=icon}
.png){kind=icon}
Return
Advancing Radar Echo Extrapolation With Hypergraph-Enhanced Latent Diffusion Model
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3596232.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Radar echo extrapolation (REE) can facilitate accurate and expeditious nowcasting of precipitation, reducing the reliance on complex numerical weather prediction (NWP) models. Spatial–temporal forecasting methods dominate this task because they can fully exploit the spatiotemporal dependencies and complex dynamic patterns inherent in radar echo data. However, they struggle with handling uncertainty and incorporating domain-specific knowledge, often resulting in blurry or unrealistic predictions. We propose a hypergraph-enhanced latent diffusion (HyDiff) model to address these limitations. The EchoDiff has been utilized to aid in accurate extrapolation. To accurately describe precipitation microphysics while adhering to the hydro-microphysical and multiscale coupling principles, the method integrates additional semantic information into the model. Specifically, the differential reflectivity factor (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Z_{\text {DR}}$ </tex-math></inline-formula>) and the differential propagation phase shift (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K_{\text {DP}}$ </tex-math></inline-formula>) are incorporated into the model as additional semantic information. Furthermore, we introduce a hypergraph neural network (HGNN) into the extrapolation method to capture correlation information across regions. The experiments show that HyDiff effectively handles uncertainty, incorporates domain-specific prior knowledge, and generates forecasts with high operational utility.
Keywords:
Auxiliary prompt
hypergraph neural network (HGNN)
latent diffusion model (LDM)
radar echo extrapolation (REE)
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W