用时序卫星图像隐式恢复地表反照率，提升山区太阳辐射估算精度。
Retrieval of Surface Solar Radiation through Implicit Albedo Recovery from Temporal Context
- 基于时空Transformer的注意力模型，从原始影像序列中自动学习地表反照率。
- 在瑞士复杂地形下，性能媲美依赖显式反照率信息的模型。
- 特别适合山区动态积雪场景，对地形复杂区域泛化能力更强。
从卫星图像准确反演地表太阳辐射（SSR）关键在于估计无云条件下的背景反射率。偏离该基准可检测云层并指导辐射传输模型推断大气衰减。现有算法通常用月均值近似背景反射率，假设地表属性变化慢于大气变化，但在多山地区常失效，因积雪间歇性与表面变化频繁。本文提出一种基于注意力机制的SSR反演模拟器，隐式从原始卫星图像序列中学习清晰天空下的地表反射率。模型基于时空视觉变换器，无需手工特征如显式反照率图或云掩膜。在瑞士地区（地形复杂、积雪动态变化）的海利蒙（HelioMont）算法瞬时SSR数据上训练，输入为欧洲第二代气象卫星（Meteosat Second Generation）的多光谱SEVIRI影像，叠加静态地形与太阳几何信息。目标变量为海利蒙算法输出的水平面总辐照度（直接+散射分量），空间分辨率为1.7 km。结果显示，在足够长的时间上下文中，该模型性能可比肩依赖显式反照率的模型，表明其能内化并利用潜在的地表反射率动态。地理分析显示，该效应在山区最为显著，并提升了简单与复杂地形设置下的泛化能力。代码与数据集已公开于https://github.com/frischwood/HeMu-dev.git。
原文摘要 · Abstract (English)
Accurate retrieval of surface solar radiation (SSR) from satellite imagery critically depends on estimating the background reflectance that a spaceborne sensor would observe under clear-sky conditions. Deviations from this baseline can then be used to detect cloud presence and guide radiative transfer models in inferring atmospheric attenuation. Operational retrieval algorithms typically approximate background reflectance using monthly statistics, assuming surface properties vary slowly relative to atmospheric conditions. However, this approach fails in mountainous regions where intermittent snow cover and changing snow surfaces are frequent. We propose an attention-based emulator for SSR retrieval that implicitly learns to infer clear-sky surface reflectance from raw satellite image sequences. Built on the Temporo-Spatial Vision Transformer, our approach eliminates the need for hand-crafted features such as explicit albedo maps or cloud masks. The emulator is trained on instantaneous SSR estimates from the HelioMont algorithm over Switzerland, a region characterized by complex terrain and dynamic snow cover. Inputs include multi-spectral SEVIRI imagery from the Meteosat Second Generation platform, augmented with static topographic features and solar geometry. The target variable is HelioMont's SSR, computed as the sum of its direct and diffuse horizontal irradiance components, given at a spatial resolution of 1.7 km. We show that, when provided a sufficiently long temporal context, the model matches the performances of albedo-informed models, highlighting the model's ability to internally learn and exploit latent surface reflectance dynamics. Our geospatial analysis shows this effect is most powerful in mountainous regions and improves generalization in both simple and complex topographic settings. Code and datasets are publicly available at https://github.com/frischwood/HeMu-dev.git
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。