A global hyperspectral soil albedo dataset for land surface modelling: Global Hyperspectral Soil Albedo Dataset (GHSAD)

Global Hyperspectral Soil Albedo Dataset (GHSAD) aims to develop a global hyperspectral soil albedo dataset suitable for application in land surface models by using the machine learning approach. We propose an integrated framework for hyperspectral soil albedo modeling that uses machine learning approaches to develop a global hyperspectral soil albedo dataset. This dataset is created based on the GSDE soil properties dataset. The GHSAD offers global hyperspectral dry and wet-soil albedo with a spatial resolution of 0.05°×0.05° and a spectral resolution of 10 nm within the range of 400-2500 nm. The GHSAD provides soil albedo under diverse soil-moisture conditions. We discretized the range of volumetric water content from dry soil to saturated soil into ten equal intervals. Soil albedo was then calculated for each resulting interval. Users have two approaches to utilize the dataset: (1) interpolating the soil albedo values across varying soil moisture levels or (2) incorporating the BSM or other more sophisticated wet-soil albedo schemes to calculate the actual soil albedo based on the dry-soil albedo provided by GHSAD. The dataset is stored in netCDF format.