Study and Prediction of Surface Deformation Characteristics of Different Vegetation Types in the Permafrost Zone of Linzhi, Tibet

Permafrost and alpine vegetation are widely distributed in Tibet, which is a sensitive area for global climate change. In this study, we inverted the surface deformation from 22 May 2018 to 9 October 2021 rectangular within city of Linzhi, using Sentinel1-A data two time-series interferometric system aperture radar (InSAR) techniques. Then, significant features were analyzed separately according different types. Finally, multiple machine learning methods used predict future deformation, results compared obtain model with highest prediction accuracy. This study aims provide scientific reference decision basis ecological security sustainable development. The showed that rate was basically between ±10 mm/a, cumulative ±35 mm. grassland, meadow, coniferous forest, all significantly correlated NDVI, effect vegetation, grassland on permafrost stronger than meadow. accuracy Holt–Winters higher Holt?s ARIMA model; it expected ground would keep rising next months, forest relatively small. above studies indicated Tibetan region stable under conditions forest. Future-related construction needs pay more attention areas meadow conditions, prone affect stability ecosystems.