GraphDOP用观测数据直接训练天气预报模型，五天内预测准确。
GraphDOP: Towards skilful data-driven medium-range weather forecasts learnt and initialised directly from observations
- 完全基于观测数据训练，不依赖物理模型再分析
- 能从卫星亮度温度等数据中学习地球系统动态特征
- 适合需要高精度中短期预报的气象研究与应用
我们提出GraphDOP，一种由欧洲中期天气预报中心（ECMWF）开发的新一代数据驱动、端到端的天气预报系统。该系统仅通过地球系统观测数据进行训练和初始化，无需任何基于物理的再分析输入或反馈。GraphDOP学习极轨和静止卫星观测的亮温等变量与常规观测测量的地球物理量之间的相关性，构建地球系统状态动态与物理过程的连贯潜在表征，并能在未来五天内对关键气象参数做出具有技巧性的预测。
原文摘要 · Abstract (English)
We introduce GraphDOP, a new data-driven, end-to-end forecast system developed at the European Centre for Medium-Range Weather Forecasts (ECMWF) that is trained and initialised exclusively from Earth System observations, with no physics-based (re)analysis inputs or feedbacks. GraphDOP learns the correlations between observed quantities - such as brightness temperatures from polar orbiters and geostationary satellites - and geophysical quantities of interest (that are measured by conventional observations), to form a coherent latent representation of Earth System state dynamics and physical processes, and is capable of producing skilful predictions of relevant weather parameters up to five days into the future.
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。