海冰密集度卫星遥感反演研究进展

Advances in Sea Ice Concentration Retrieval Based on Satellite Remote Sensing

海冰密集度是海冰的重要参数之一,在冰区导航、海上作业、海冰模式验证和气候模型改进等方面具有重要意义。卫星遥感具有覆盖范围广、重访周期短、成本相对低等优势,已成为获取海冰密集度的主要观测手段。本文从主被动微波遥感和光学遥感的角度,回顾了现阶段海冰密集度卫星遥感反演研究进展情况,包括海冰监测传感器、海冰密集度反演算法和海冰密集度产品等。结果表明,被动微波遥感是目前获取海冰密集度的主要方式,已发展出许多成熟的业务化算法;主动微波遥感数据已成为制作冰情图的主要数据源,海冰密集度反演算法由合成孔径雷达SAR(Synthetic Aperture Radar)图像分类向深度学习算法发展;光学遥感海冰密集度算法较为成熟,但受限于云层和夜晚限制,其反演结果多用于其他海冰密集度产品的验证。受传感器硬件限制,3种观测手段各有其长处与不足。为获得高精度、高时空分辨率的海冰密集度数据,开展多源数据融合研究是解决传感器性能瓶颈的有效手段。大数据时代,基于深度学习的海冰密集度卫星遥感反演技术快速发展,需要深度融入海冰密集度卫星遥感领域知识。海冰密集度卫星遥感反演应着力于海冰预报服务,致力于提高我国的海冰预报能力。

Sea ice concentration is one of the important parameters of sea ice,which plays an important role in ice navigation,offshore operations,sea ice model verification and climate model improvement.Satellite remote sensing has the advantages of wide coverage,short revisit period and low cost,and has become the main observation method to obtain sea ice concentration.From the perspectives of active and passive microwave remote sensing as well as optical remote sensing,this paper reviews the current research progress in satellite remote sensing retrieval of sea ice concentration,including sea ice monitoring sensors,sea ice concentration inversion algorithms,and sea ice concentration products.The results show that passive microwave remote sensing is the main method to obtain sea ice concentration at present,and many mature operational algorithms have been developed.Active microwave remote sensing data has become the main data source of sea ice charts.The sea ice concentration retrieval algorithms are developed from SAR image classification to deep learning.The sea ice concentration algorithms based on optical remote sensing are relatively mature,but limited by the clouds and the night,and their results are usually used for other products’validation.Limited by the sensors’hardware,the three observation methods have their own advantages and disadvantages.In order to obtain sea ice concentration with high precision and high spatial and temporal resolution,multi-source data fusion is an effective means to solve the bottleneck of sensor performance.As satellite remote sensing enters the era of big data,the sea ice concentration retrieval technology based on deep learning develops rapidly,which requires deep integration of satellite remote sensing knowledge of sea ice concentration.Satellite remote sensing retrieval of sea ice concentration should serve sea ice forecasting and improve the country’s sea ice forecasting ability.