发表机构
Massachusetts Institute of Technology; European Space Agency; University of Nottingham; Hong Kong Polytechnic University; Hochschule Bonn-Rhein-Sieg University of Applied Sciences; Stanford University; The University of Texas at Dallas; Mines Paris, Université PSL; Technical University of Denmark（麻省理工学院; 欧洲空间局; 诺丁汉大学; 香港理工大学; 波恩-莱茵-锡格应用科学大学; 斯坦福大学; 德克萨斯大学达拉斯分校; 巴黎矿业大学（巴黎文理研究大学）; 丹麦技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SolarBench是一个全球开放的基于图像的太阳能即时预测基准，整合了11个站点十年间超过六百万张天空和卫星图像，用于公平评估模型并揭示平均精度与捕捉快速波动能力之间的差距。
AI 中文摘要
随着太阳能发电占比的增长，对天气驱动的太阳能波动进行即时预测（nowcasting）对于能源系统的可靠运行变得至关重要。最先进的方法越来越多地将深度学习应用于天空相机和地球静止卫星观测，但数据集的碎片化和评估标准的不一致使得难以判断所报告的性能提升是否能在不同气候、云况和光伏（PV）系统中得到泛化。为此，我们推出了SolarBench，一个基于图像的太阳能即时预测的开放全球基准。SolarBench整合了来自11个不同站点、跨越十年的超过六百万张天空和卫星图像，并附有辐照度或光伏输出数据以及辅助大气数据。配套的工具箱支持可复现的数据访问、处理、模型开发和评估。利用SolarBench，我们对代表性模型进行了基准测试，并揭示了平均预测精度与捕捉快速太阳能波动能力之间的差距。我们进一步量化了不同云况下的可预测性，并展示了向新光伏系统进行数据高效迁移的能力。SolarBench为太阳能即时预测领域的公平比较和方法创新提供了一个可扩展的基础。
英文摘要
As the share of solar power grows, nowcasting weather-driven solar variability becomes critical for reliable energy system operation. State-of-the-art approaches increasingly apply deep learning to sky camera and geostationary satellite observations, but fragmented datasets and inconsistent evaluation make it difficult to determine whether reported improvements generalize across climates, cloud regimes, and photovoltaic (PV) systems. Here we introduce SolarBench, an open global benchmark for image-based solar nowcasting. SolarBench harmonizes more than six million sky and satellite images from 11 diverse sites spanning a decade, together with irradiance or PV output and auxiliary atmospheric data. An accompanying toolbox supports reproducible data access, processing, model development, and evaluation. Using SolarBench, we benchmark representative models and reveal a gap between average forecasting accuracy and the ability to capture rapid solar fluctuations. We further quantify predictability across cloud regimes and demonstrate data-efficient adaptation to new PV systems. SolarBench provides an extensible foundation for fair comparison and methodological innovation in solar nowcasting.
