hide
Free keywords:
Deep Learning, GNSS Reflectometry, Cyclone GNSS (CYGNSS)
Abstract:
Vegetation water content (VWC) is a crucial parameter for understanding vegetation dynamics and the hydrological cycle on Earth. Spaceborne global navigation satellite system reflectometry (GNSS-R) has demonstrated promising potential in vegetation monitoring. To address the lack of large-scale datasets and foster algorithmic innovation, we introduce a triplet dataset, termed as CGS dataset, which consists of measurements from the cyclone GNSS (CYGNSS), global land data assimilation system (GLDAS), and soil moisture active passive (GLDAS). With a timespan of over three years, observations from these missions are aggregated, filtered, and collocated with standardized quality control and spatiotemporal alignment. The CGS dataset includes variables that describe reflected signal characteristics, surface attributes, and hydrological parameters to support reproducibility and enable further analyses.
