Time-series InSAR and Random Forest Method

Ground deformation is an important index for evaluating the stability and degradation of the permafrost. Due to 8 limited accessibility, in-situ measurement of the ground deformation of permafrost area on the Tibetan Plateau is a challenge. 9 Thus, the technique of time-series Interferometric Synthetic Aperture Radar (InSAR) is often adopted for measuring the ground 10 deformation of the permafrost area, the effectiveness of which is however degraded in the areas with geometric distortions in 11 Synthetic Aperture Radar (SAR) images. In this study, a method that integrates InSAR and random forest method is proposed for 12 an improved permafrost stability mapping on the Tibetan Plateau; and, to demonstrate the application of the proposed method, 13 the permafrost stability mapping in a small area located in the central region of the Tibetan Plateau is studied. First, the ground 14 deformation in the concerned area is studied with InSAR, in which 67 Sentinel-1 scenes taken in the period from 2014 to 2020 15 are collected and analyzed. Second, the relationship between the environmental factors (i.e., topography, land cover, land surface 16 temperature, and distance-to-road) and the permafrost stability is mapped with the random forest method, based on the high17 quality data extracted from initial InSAR analysis. Third, the permafrost stability in the areas where the visibility of SAR images 18 is poor or the InSAR analysis results are not available is mapped with the trained random forest model. Comparative analyses 19 demonstrate that the integration of InSAR and random forest method yields a more effective permafrost stability mapping, 20 compared to the sole application of InSAR analysis. 21