The Kubuqi Desert represents a key ecologically fragile region in northern China, primarily functioning as a windbreak and sand-fixation barrier while also contributing to regional ecological balance. However, the area's ecological vulnerability is pronounced, and investigating the spatiotemporal dynamics of vegetation carbon storage and associated driving mechanisms is essential for the scientific formulation of ecological restoration strategies. This research incorporates multi-source remote-sensing datasets (including Landsat 8 OLI/TIRS Level 2, Sentinel-1 Synthetic Aperture Radar (SAR), ERA5 daily meteorological data, GEDI Level 4B, SRTM GL1 v003, and ESA WorldCover v100) based on the Google Earth Engine (GEE) platform, and employs multiple machine-learning algorithms (validation metrics of the machine learning model: R2 = 0.917, RMSE = 0.251) to develop a dynamic monitoring model of vegetation carbon storage in the Kubuqi Desert during the period 2019-2023. The analysis systematically evaluates the influence of climatic variables and anthropogenic activities on the spatiotemporal differentiation of carbon storage. The results indicate a slight upward trend in overall carbon storage across the study area (average annual increase of 0.4%), with high values predominantly concentrated in vegetated regions (up to 5.22 Mg/Ha) and low values distributed in bare lands and desert zones (0.5-0.7 Mg/Ha). Altitude, temperature, and slope serve as the primary driving factors governing carbon-storage variability. The findings suggest that scientifically guided vegetation restoration and optimized water-resource management can enhance the carbon-sink capacity of the Kubuqi Desert, offering a robust scientific basis for ecological governance and carbon budget assessment in arid and semi-arid desert ecosystems.