Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution

2025-02-09

AI Summary

To address the large retrieval errors in local meteorological states caused by the low spatial resolution of satellite remote-sensing weather data (e.g., GridSat), this paper proposes a satellite-observation-guided zero-shot conditional diffusion model for high-fidelity, arbitrary-resolution meteorological field downscaling. Methodologically: (i) we formulate a diffusion-based generative framework conditioned on coarse-resolution satellite observations; (ii) we incorporate cross-modal attention to jointly fuse GridSat observations with high-resolution ERA5 reanalysis data; and (iii) we design learnable convolutional kernels to physically model the upsampling process and integrate a tiling strategy to support flexible output resolutions. Without fine-tuning, the model directly generates 6.25 km resolution meteorological fields, significantly outperforming conventional interpolation and state-of-the-art downscaling methods in key variables—including temperature and humidity—while markedly improving spatial structural consistency and observational fidelity.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate acquisition of surface meteorological conditions at arbitrary locations holds significant importance for weather forecasting and climate simulation. Due to the fact that meteorological states derived from satellite observations are often provided in the form of low-resolution grid fields, the direct application of spatial interpolation to obtain meteorological states for specific locations often results in significant discrepancies when compared to actual observations. Existing downscaling methods for acquiring meteorological state information at higher resolutions commonly overlook the correlation with satellite observations. To bridge the gap, we propose Satellite-observations Guided Diffusion Model (SGD), a conditional diffusion model pre-trained on ERA5 reanalysis data with satellite observations (GridSat) as conditions, which is employed for sampling downscaled meteorological states through a zero-shot guided sampling strategy and patch-based methods. During the training process, we propose to fuse the information from GridSat satellite observations into ERA5 maps via the attention mechanism, enabling SGD to generate atmospheric states that align more accurately with actual conditions. In the sampling, we employed optimizable convolutional kernels to simulate the upscale process, thereby generating high-resolution ERA5 maps using low-resolution ERA5 maps as well as observations from weather stations as guidance. Moreover, our devised patch-based method promotes SGD to generate meteorological states at arbitrary resolutions. Experiments demonstrate SGD fulfills accurate meteorological states downscaling to 6.25km.

Problem

• Accurate meteorological state acquisition
• High-resolution downscaling from satellite data
• Zero-shot guided sampling strategy

Innovation

• Conditional diffusion model
• Attention mechanism fusion
• Patch-based resolution method