用扩散模型从卫星数据生成高精度雷达反射率图
DiffSR: Learning Radar Reflectivity Synthesis via Diffusion Model from Satellite Observations
- 两阶段扩散模型：先重建后精修，融合卫星与雷达数据
- 生成细节更丰富，高价值对流区域还原更准确
- 适合气象监测、灾害预警等需要高分辨率雷达数据的场景
天气雷达数据合成可填补地面观测缺失区域的数据空白。现有方法多采用基于重建的MSE损失模型，从卫星观测中恢复雷达数据，但常导致过平滑，难以生成高频细节或对流天气相关的高价值区域。为此，我们提出一种两阶段扩散模型DiffSR：首先在全局尺度数据上预训练重建模型获取雷达估计，再将雷达估计结果与卫星数据联合作为条件，输入扩散模型生成雷达反射率。大量实验表明，该方法达到当前最优（SOTA）性能，具备生成高频细节和高价值区域的能力。
原文摘要 · Abstract (English)
Weather radar data synthesis can fill in data for areas where ground observations are missing. Existing methods often employ reconstruction-based approaches with MSE loss to reconstruct radar data from satellite observation. However, such methods lead to over-smoothing, which hinders the generation of high-frequency details or high-value observation areas associated with convective weather. To address this issue, we propose a two-stage diffusion-based method called DiffSR. We first pre-train a reconstruction model on global-scale data to obtain radar estimation and then synthesize radar reflectivity by combining radar estimation results with satellite data as conditions for the diffusion model. Extensive experiments show that our method achieves state-of-the-art (SOTA) results, demonstrating the ability to generate high-frequency details and high-value areas.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。