湿地植被在固碳过程中扮演重要角色。作为高寒湿地生态系统的典型代表,若尔盖湿地的植被分类与变化监测对于研究其碳汇功能具有重要意义。光学遥感和微波遥感在植被监测中各有其优缺点,因此本研究提出结合Sentinel-2光学数据和Sentinel-1 合成孔径雷达(Synthetic Aperture Radar, SAR)数据的若尔盖湿地植被分类与变化监测方法。基于动态时间归整算法(Dynamic Time Warping,DTW)提取Sentinel-1 SAR数据的时间序列物候特征,结合Sentinel-2多光谱数据的光谱特征,以2020年实地获取的植被样本及使用样本迁移得到的2017年样本,通过随机森林算法分别对两个时期的若尔盖湿地植被进行分类并对其变化进行分析。研究表明：(1)结合Sentinel-1和Sentinel-2数据,充分发挥各自多时相、多光谱的优势对若尔盖湿地植被进行分类得到可靠的分类结果,总精度达到了97.43%,Kappa系数为0.96。(2)基于样本迁移原理,本研究通过将2020年实地采集的样本迁移至2017年,解决了历史时期实地样本不可得的问题,并针对SAR数据的特点提出基于DTW的样本迁移方法,顺利实现了2017年的植被分类过程。（3）通过对2017-2020年植被变化进行分析，发现近年来若尔盖湿地植被总体变化不大，演变类别以恢复演替为主，约占研究区面积的7%。

Wetland vegetation plays an important role in the process of carbon sequestration. As a typical alpine wetland ecosystem, Ruoerge wetland has been attracting more and more attentions due to its carbon sink function, which makes the classification and change detection of its vegetation coverage crucial. Optical remote sensing and microwave remote sensing have their own advantages and disadvantages for these purposes. This study, therefore, proposes a method to map the vegetation of Ruoerge wetland and monitor its change by integrating Sentinel-2 optical data and Sentinel-1 synthetic aperture radar (SAR) data. Based on the dynamic time warping (DTW) algorithm to extract the time-series physical characteristics of Sentinel-1 SAR data, combined with the spectral characteristics of Sentinel-2 multispectral data, in situ vegetation samples obtained by UAV in 2020 were used and migrated to 2017 for classifying and analyzing the vegetation changes of Ruoerge wetland from 2017-2020 using random forest algorithm. Research results show that: (1) Combining Sentinel-1 and Sentinel-2 data, their respective multi-temporal and multi-spectral advantages were fully exploited to obtain reliable classification results with an overall accuracy of 97.43% and a Kappa coefficient of 0.96. (2) Based on the principle of sample migration, this study solved the problem that the field samples were not available in the historical period (2017). we developed a sample migration method based on DTW according to the characteristics of SAR data, thus successfully realizing the vegetation classification in 2017. (3) Vegetation changes analysis from 2017 to 2020 indicates that vegetations in Ruoerge wetlands remain overall unchanged in recent years, with the changed area exhibiting a recovery trend (~7% of the total area).