云是大气热力平衡和水气循环的重要环节，对气候模式和天气预报有着重要影响。鉴于云在大气科学研究中的重要地位以及观测的复杂性，本项目以国家重大应用需求为牵引，充分利用天基卫星观测、空基探空仪资料、地基激光、可见光和红外探测的优势互补，针对复杂大气环境下多源协同的云点/云层识别、基于大数据驱动的云类特征表示与学习和卫星/地面观测云量融合的时空泛化等关键科学问题，以模式识别为核心方法和融合基础，研究地基遥感协同的云量计算、云类识别；地空协同的云垂直结构识别；卫星云探测空间分辨率下的卫星、地面观测的云量融合等协同测云关键技术，用地基云自动观测资料和探空资料对卫星云观测资料进行修正和完善。协同处理后的云资料既有卫星观测的广度，又有地基观测的精度，是目前常规分立探测手段所不能比拟的，有望提升我国的气象预报预测能力和防灾减灾能力，同时研究成果也可为将来地面气象自动观测站和探空站的合理布局提供科学依据。

Cloud is one of the most important forces of Earth’s heat balance and hydrological cycle. The net effect of clouds, however, is still unknown and it plays important role in climate models, climate predictions and meteorological services. Because of the importance of the clouds in the atmospheric science research and the complexity of cloud observation, this project takes national important application demand for traction, makes full use of space-based satellite observation, radiosonde data, ground based laser, visible light and infrared observation of complementary advantages, aiming at the key scientific problems: multi-source collaborative cloud recognition in the complex atmospheric environment, big-data driven cloud feature representation and learning , satellite/ground cloud cover fusion and its spatio-temporal generalization. The research will focus on revising and improving the satellite cloud observation using ground based cloud observation and radiosonde data. The key techniques will be investigated in the view of pattern recognition separately, including cloud cover calculation and cloud type recognition based on fusion of ground based remote sensing, cloud vertical structure identification using ground-air coordination, and cloud cover fusion under the satellite cloud observation’s spatial resolution based on Space-Air-Ground integrated cloud observation. The products by Space-Air-Ground integrated cloud observation can improve the quality of cloud data both in breadth and precision beyond the separated cloud observations, which is expected to enhance our ability of weather forecast and disaster prevention. At the same time, the result of research can help for the reasonable layout of future ground based automatic meteorological observation stations and radiosonde stations establishment.