OCELOT：使用图-Transformer混合模型从异构地球观测进行直接大气预测
OCELOT: Direct Atmospheric Forecasting from Heterogeneous Earth Observations Using a Graph-Transformer Hybrid Model
浏览论文内容
中文总结 AI 辅助
研究提出OCELOT系统，能直接根据异构观测预测未来地球观测。它结合多种组件，在观测空间运行。经训练、验证和评估，结果显示其能生成连贯预测，虽精度低于GFS，但优于持续性预测，可恢复大气结构并提供短期技能。
中文摘要 AI 辅助
本研究提出了OCELOT（用于展望轨迹的以观测为中心的估计和学习），这是一个全球机器学习预测系统，可直接根据异构卫星和现场测量预测未来的地球观测。与基于网格化再分析状态训练的数据驱动天气模型不同，OCELOT在观测空间中本地运行，保留仪器特定的采样、观测几何和测量特征。该系统结合了每个仪器的图注意力编码器、共享的球面二十面体潜在网格、混合滑动窗口Transformer/空间图神经网络处理器和元数据条件解码器，以生成提前12小时的预测。OCELOT在2015年至2023年的观测数据上进行训练，在2024年进行验证，并在2025年的卫星辐射、探空仪、飞机和地面网络观测数据上进行样本外评估。在2025年的评估中，OCELOT在独立观测系统中生成了空间连贯的+12小时预测：微波温度探测通道的RMSE值为1.24-1.87K，而对地表和云更敏感的AVHRR红外窗口通道的RMSE值更高，为3.95K。垂直剖面诊断显示探空仪和飞机温度结构在物理上是一致的。地表预测在12小时内保持稳定，2米气温RMSE从+3小时的约3.2K增加到+12小时的约3.6K。在成对的观测空间比较中，OCELOT在2米温度和10米风分量的较长提前期内，精度仍低于运行中的GFS，但远优于持续性预测。这些结果表明，观测空间预测可以恢复大规模大气结构，并在没有再分析监督的情况下提供有意义的短期技能。
英文摘要
This study presents OCELOT (Observation-Centric Estimation and Learning for Outlook Trajectories), a global machine-learning forecasting system that predicts future Earth observations directly from heterogeneous satellite and in-situ measurements. Unlike data-driven weather models trained on gridded reanalysis states, OCELOT operates natively in observation space, preserving instrument-specific sampling, viewing geometry, and measurement characteristics. The system combines per-instrument graph-attention encoders, a shared spherical icosahedral latent mesh, a hybrid sliding-window Transformer/spatial graph neural network processor, and metadata-conditioned decoders to produce forecasts up to 12 h ahead. OCELOT is trained on observations for the years 2015 through 2023, validated on the year 2024, and evaluated out of sample on 2025 observations across satellite radiances, radiosondes, aircraft, and surface networks. In the 2025 evaluation, OCELOT produces spatially coherent +12 h forecasts across independent observing systems: microwave temperature-sounding channels show RMSE values of 1.24-1.87 K, while the more surface- and cloud-sensitive AVHRR infrared window channel shows a higher RMSE of 3.95 K. Vertical profile diagnostics show physically consistent radiosonde and aircraft temperature structure. Surface forecasts remain stable through 12 h, with 2-m air-temperature RMSE increasing from about 3.2 K at +3 h to about 3.6 K at +12 h. In paired observation-space comparisons, OCELOT remains less accurate than operational GFS but substantially outperforms persistence at longer lead times for 2-m temperature and 10-m wind components. These results demonstrate that observation-space forecasting can recover large-scale atmospheric structure and provide meaningful short-range skill without reanalysis supervision.
