RESEARTH ON THE DETECTION METHOD OF ANTARCTIC ICE SHEET FREEZING AND THAWING BASED ON GEE AND SENTINEL-1 DATA

Based on Sentinel-1 EW mode data and GEE platform, this paper proposes an Antarctic ice sheet freezing and thawing detection method based on change detection and decision tree. On the GEE platform, first of all, the median value of the Sentinel-1 data in the winter months of June, July and August is as a base image set, then the difference between the summer and the base image of the same orbit is detected. At last, the thresholds of both the elevation and the backscattering coefficient difference are used to judge the freezing state of the Antarctic ice sheet. Use this method, the monthly update information on the freezing and thawing of the Antarctic ice sheet from October 2016 to March 2017, and from October 2017 to March 2018 are obtained. For the detection results, the accuracy of the self-selected samples and automatic weather station data is used for verification. The average overall accuracy of the self-selected sample verification is 93%, the average Kappa coefficient is 0.90, and the average accuracy of the automatic weather station verification is 83.86%.