发表机构
Finnish Meteorological Institute; Aalto University（芬兰气象研究所; 阿尔托大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究开发了CloudCast v2机器学习模型，经再分析数据训练后适配卫星云场，使12小时云量预报的平均绝对误差降低10%，突破了传统1-3小时临近预报的时间限制并保留空间细节。
AI 中文摘要
准确的云量预报对温度预测、辐射预报和太阳能运营至关重要。短期预报方法能在预报最初几小时内保持观测到的云分布，但当云场经历形成、消散和变形时，其预报技能会下降。较长的预报时效需要考虑大气演变，但业务数值天气预报（NWP）在初始化时可能无法准确表示卫星观测到的云状态。我们开发了CloudCast v2，这是一款基于观测初始化条件的12小时云量预报机器学习模型。该模型首先在哥白尼欧洲区域再分析数据集（Ridal2024）上训练，以学习云演变动力学，随后使用条件流匹配（Lipman2023，一种生成式方法，可在观测到的初始云场和NWP输入的条件下，将噪声转化为云量预报）适配到卫星衍生的云场。在1至12小时的范围内，CloudCast v2相比其前身CloudCast v1（Partio2025）将平均绝对误差降低了10%；在空间一致性的邻域度量分数技巧得分上，根据云量类别不同，CloudCast v2在约3至6小时后超过CloudCast v1。这些结果表明，基于观测初始化的机器学习预报可突破通常1至3小时的临近预报范围，同时保留卫星云场的空间细节。
英文摘要
Accurate cloud-cover forecasts are important for temperature prediction, radiation forecasting, and solar-power operations. Short-range forecasting methods can preserve observed cloud placement during the first forecast hours, but their skill decreases when cloud fields evolve through formation, dissipation and deformation. Longer lead times require accounting for atmospheric evolution, but operational numerical weather prediction (NWP) forecasts may not accurately represent the satellite-observed cloud state at initialization. We develop CloudCast v2, a machine-learning model for 12-hour cloud-cover forecasting from observation-based initial conditions. The model is first trained on the Copernicus European Regional Reanalysis (Ridal2024) to learn cloud-evolution dynamics, and is then adapted to satellite-derived cloud fields using conditional flow matching (Lipman2023), a generative method that transforms noise into cloud-cover forecasts conditioned on the observed initial cloud fields and NWP inputs. CloudCast v2 reduces mean absolute error by 10% relative to its predecessor, CloudCast v1 (Partio2025), over the 1-12 h range. It also overtakes CloudCast v1 in fractions skill score, a neighborhood-based measure of spatial agreement, after approximately 3-6 h, depending on the cloudiness category. These results show that observation-initialized machine-learning forecasts can extend beyond the usual 1-3-hour nowcasting range while retaining spatial detail from satellite cloud fields.
