1980-2019全球海气通量（潜热通量）和SST数据集

本数据集由中科院海洋大科学研究中心共建单位中科院南海海洋研究所王鑫研究员和张荣望助理研究员牵头研制，主要基于卫星遥感和再分析数据，以中国近海浮标、海上平台和通量塔等观测数据为训练数据，采用卷积神经网络深度学习和改进后的COARE 3.5算法等技术研发，有效克服了中等大气比湿条件下的潜热通量低估和海表冷皮效应造成的潜热通量误差等突出问题。与国际主流海气通量产品对比，该产品在中国近海具有显著的区域优势和性能指标优势。

This dataset was developed under the leadership of Researcher WANG Xin and Assistant Researcher ZHANG Rongwang from the South China Sea Institute of Oceanology, Chinese Academy of Sciences (CAS), a co-construction unit of the CAS Ocean Science Research Center. It was mainly developed based on satellite remote sensing and reanalysis data, using observational data from buoys, offshore platforms, flux towers and other facilities in China's offshore waters as training datasets, with technologies including convolutional neural network (CNN) deep learning and the improved COARE 3.5 algorithm. This product effectively addresses key issues such as the underestimation of latent heat flux under moderate atmospheric specific humidity conditions and latent heat flux errors caused by the sea surface cold skin effect. Compared with mainstream international air-sea flux products, this dataset demonstrates significant regional and performance advantages in China's offshore waters.

搜集汇总

背景与挑战

背景概述

该数据集为1980-2019年全球海气通量（潜热通量）和SST数据，基于卫星遥感和再分析数据，采用深度学习技术研发，在中国近海具有显著的区域优势。数据集包含栅格格式的潜热通量和海表温度数据，存储容量为616.56 MB。