基于重轨InSAR的积雪深度反演方法

Snow depth derived from repeat-pass InSAR sounding

利用合成孔径雷达(Synthetic Aperture Radar,SAR)反演积雪深度是流域尺度积雪遥感监测的热点之一,SAR的干涉测量(Interferometic SAR,InSAR)扩展了其在积雪研究中的应用.微波能够穿透干雪,并在雪-空气界面发生折射,导致传播路径变化;根据InSAR原理,降雪前后的SAR像对会形成由于干雪覆盖导致的干涉相位差.基于此,提出了基于重轨InSAR技术的积雪深度反演方法:首先,结合气象、水文、野外观测数据,判断积雪状态,以选择最佳干涉像对(无雪和干雪覆盖);然后,优化干涉处理过程,利用差分原理,获得由于干雪覆盖导致的相位差;最后,基于雪深与相位差的几何关系,反演积雪深度,并探讨反演结果精度的影响因素.以新疆玛纳斯河流域山前平原为研究区,利用Envisat ASAR数据,实现积雪深度的反演.结果表明:2009年2月份研究区大部分地区雪深为20 cm左右,与野外观测结果相符;与同时期HJ-1光学影像比较,所获得的积雪覆盖范围吻合.同时指出,失相干和输入参数(入射角、雪密度)误差是反演结果误差的主要来源.

Snow depth is one of the most important parameters in hydrology. At a regional scale, SAR （ Synthetic Aperture Radar） has the ability to monitor the surface deformation effectively, with a certain penetration and interference sounding capability. The refraction of microwaves in dry snow is shown to have a significant effect on the interferometric phase. A relationship between changes in snow depth and interferometric phase can be derived. A method of snow depth derived from repeatpass InSAR （Interferometic SAR） sounding by using Envisat ASAR IMS products is proposed. Taking the pediment plain in Manas River basin as a study area, the optimal InSAR pair （with and without snow） is chosen by judging snow state from meteorology and hydrology ob servations, as well as field observation data, then the interferometric phase can be calculated as a product of In SAR optimized processing. From the derived snow depth in the period between Jul. 2008 and Feb. 2009, it was pictured that the average snow depth was about 20 cm in the study area, which was consistent with the field survey. Compared with satellite snow cover images from HJ-1, one can see that the snow cover is similar with the optical images and the snow depth distribution varies with the mixed pixels in HJ-1 data identically. Finally, error evaluation was proposed to deal with the possible unreasonable results. Some reasons which cause inaccuracy were also discussed, such as decoherence due to snow cover and atmospheric effects.