发表机构
STACC OÜ（STACC 有限责任公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出多成像仪多分辨率CNN架构，结合MSG/SEVIRI与MTG/FCI影像等反演北欧爱沙尼亚10分钟SSI，发现MTG/FCI影像可提升云主导下的SSI反演精度，但无法解决晴空下的局限。
AI 中文摘要
准确的地表太阳辐照度（SSI）估算对光伏能源监测与预测愈发重要。新近推出的第三代气象卫星（MTG）星座提供的成像数据，空间分辨率高于第二代气象卫星（MSG）星座，但它对基于机器学习的SSI反演的益处尚未得到充分证实。本研究中，我们引入了一种多成像仪、多分辨率卷积神经网络（CNN）架构，用于针对北欧爱沙尼亚地区的10分钟SSI反演，所用数据包括MSG/SEVIRI与MTG/FCI卫星影像，以及太阳几何特征、晴空辐照度特征。模型性能通过爱沙尼亚8个气象站的地面日射强度计测量值，采用站点交叉验证与多个训练种子进行评估，同时还与基于物理的卫星SSI产品SARAH-3进行了对比。混合SEVIRI-FCI模型在阴天和多云条件下的表现显著优于仅使用SEVIRI的模型，分别将均方根误差（RMSE）降低了8.2 W m⁻²和5.7 W m⁻²；但在少云或晴空条件下，混合SEVIRI-FCI模型与仅SEVIRI模型的RMSE未观测到统计学意义上的显著差异。与基于物理的SARAH-3相比，混合模型在阴天条件下的技巧得分为35%，多云条件下为21%，整体为20%；此外，两种模型在晴空条件下的表现均逊于SARAH-3。这些结果表明，当云主导辐照度变异性时，更高分辨率的MTG/FCI影像可改进基于CNN的SSI反演，但也说明仅更高的空间分辨率不足以解决基于机器学习的SSI反演在晴空条件下的局限性。
英文摘要
Accurate Surface Solar Irradiance (SSI) estimation is increasingly important for photovoltaic energy monitoring and forecasting. The recently introduced Meteosat Third Generation (MTG) satellite constellation provides imaging data with higher spatial resolution compared to the Meteosat Second Generation (MSG) satellite constellation, but its benefits for machine-learning-based SSI retrieval have not been well established. In this work, we introduce a multi-imager and multi-resolution convolutional neural network architecture for 10-minute SSI retrieval over Northern Europe (Estonia) using MSG/SEVIRI and MTG/FCI satellite imagery together with solar-geometry and clear-sky irradiance features. Model performance is evaluated against ground-based pyranometer measurements from eight Estonian meteorological stations using site-based cross-validation and multiple training seeds. Model performance is also compared with the SARAH-3 physics-based satellite SSI product. The hybrid SEVIRI-FCI model significantly outperformed the SEVIRI-only model under overcast and cloudy conditions, reducing RMSE by 8.2 W m$^{-2}$ and 5.7 W m$^{-2}$, respectively. However, under partly cloudy or clear skies, no statistically significant difference in RMSE was observed between the SEVIRI-FCI hybrid and the SEVIRI-only models. Compared with physics-based SARAH-3, the hybrid model yielded skill scores of 35 % under overcast conditions, 21 % under cloudy conditions, and 20 % overall. Furthermore, both models underperformed SARAH-3 in clear-sky conditions. These results show that higher-resolution MTG/FCI imagery improves CNN-based SSI retrieval when clouds dominate irradiance variability, but also indicate that higher spatial resolution alone is insufficient to address clear-sky limitations in machine-learning-based SSI retrieval.
