Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces PuYun-LDM, a latent diffusion model for high-resolution ensemble weather forecasting that addresses the limited diffusability of LDMs in this domain. To improve diffusability, the authors incorporate weather-state evolution features encoded by a 3D Masked AutoEncoder (3D-MAE) as additional conditioning. They also propose a Variable-Aware Masked Frequency Modeling (VA-MFM) strategy to adaptively regularize the spectral energy distribution of each variable, leading to improved performance compared to ENS at short lead times.
By encoding weather-state evolution and adaptively regularizing spectral frequencies, PuYun-LDM overcomes the diffusability limitations of latent diffusion models, enabling high-resolution ensemble weather forecasts with superior short-term accuracy and efficient parallel generation.
Latent diffusion models (LDMs) suffer from limited diffusability in high-resolution (<=0.25{\deg}) ensemble weather forecasting, where diffusability characterizes how easily a latent data distribution can be modeled by a diffusion process. Unlike natural image fields, meteorological fields lack task-agnostic foundation models and explicit semantic structures, making VFM-based regularization inapplicable. Moreover, existing frequency-based approaches impose identical spectral regularization across channels under a homogeneity assumption, which leads to uneven regularization strength under the inter-variable spectral heterogeneity in multivariate meteorological data. To address these challenges, we propose a 3D Masked AutoEncoder (3D-MAE) that encodes weather-state evolution features as an additional conditioning for the diffusion model, together with a Variable-Aware Masked Frequency Modeling (VA-MFM) strategy that adaptively selects thresholds based on the spectral energy distribution of each variable. Together, we propose PuYun-LDM, which enhances latent diffusability and achieves superior performance to ENS at short lead times while remaining comparable to ENS at longer horizons. PuYun-LDM generates a 15-day global forecast with a 6-hour temporal resolution in five minutes on a single NVIDIA H200 GPU, while ensemble forecasts can be efficiently produced in parallel.