发表机构
LATMOS; IPSL; UVSQ Université Paris-Saclay; Sorbonne Université; CNRS; Inria（大气、环境与空间观测实验室; 皮埃尔-西蒙·拉普拉斯研究所; 凡尔赛-圣康坦大学（巴黎-萨克雷大学）; 索邦大学; 法国国家科学研究中心; 法国国家信息与自动化研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究系统比较了确定性U-Net、Transformer、条件GAN和扩散模型在法国区域红外亮温降水反演中的表现，发现生成模型虽牺牲像素精度但能更好捕捉极端降水，为平衡精度与变率提供指导。
AI 中文摘要
精细空间尺度的准确降水估计对水文学、农业和气候研究至关重要。来自地球静止卫星的红外亮温在大陆尺度区域上提供了极佳的时间覆盖。然而，由于这些测量主要表征云顶特性而非近地表降水过程，它们与降雨强度的相关性有限，使得定量降水估计颇具挑战。在本研究中，我们对用于从法国本土上空第二代气象卫星红外亮温进行高分辨率降水反演的最新深度学习模型进行了系统性相互比较。这些模型包括确定性U-Net、基于Transformer的架构、条件生成对抗网络（GAN）和扩散模型。我们构建了一个涵盖2008年至2023年的精选数据集，将法国气象局雷达拼图作为参考，结合多通道红外观测，并设计了预处理和采样策略以应对降雨的重尾分布和间歇性特征。我们的结果表明，确定性模型提供稳健的平均估计并在像素级精度上表现出色，但系统性地低估极端降水。相比之下，生成模型能更好地捕捉完整的降水分布，包括罕见和强降雨事件，产生更真实的空间结构，但代价是像素级保真度降低。这些结果凸显了像素级精度与降水变率之间的权衡，表明生成方法在极端事件检测和概率应用中具有优势。这项工作为评估基于红外降水的反演方法建立了一个可复现的框架，并为设计平衡精度、变率和极端事件表征的模型提供了指导。
英文摘要
Accurate precipitation estimation at fine spatial scales is critical for hydrology, agriculture, and climate studies. Infrared brightness temperatures from geostationary satellites offer excellent temporal coverage over continental-scale domains. However, because these measurements primarily characterize cloud-top properties rather than precipitation processes near the surface, their correlation with rainfall intensity remains limited, making quantitative precipitation estimation challenging. In this study, we conduct a systematic inter-comparison of state-of-the-art deep learning models for high-resolution precipitation retrieval from Meteosat Second Generation infrared brightness temperatures over metropolitan France. These models include deterministic U-Nets, transformer-based architectures, conditional GANs, and diffusion models. We construct a curated dataset spanning 2008--2023, combining M{é}t{é}o-France radar mosaics as reference with multi-channel infrared observations, and design preprocessing and sampling strategies to address the heavy-tailed, intermittent nature of rainfall. Our results show that deterministic models provide robust mean estimates and excel in pixel-wise accuracy, but systematically underestimate extreme precipitation. In contrast, generative models better capture the full precipitation distribution, including rare and heavy rainfall events, producing more realistic spatial structures at the cost of reduced pixel-wise fidelity. These results highlight a trade-off between pixel-wise accuracy and precipitation variability, showing that generative approaches are advantageous for extreme-event detection and probabilistic applications. This work establishes a reproducible framework for evaluating infrared- based precipitation retrieval methods and provides guidance for designing models that balance precision, variability, and extreme-event representation.
