GLC_FCS10: global 10 m land-cover dataset with fine classification system from Sentinel-1 and 2 time-series data

Although the global 10 m land-cover products have made a lot progresses over past few years, their simple classification system is difficult to meet the needs of diverse applications.GLC_FCS10 is a novel global 10 m land cover product in 2023 generated from time-series Sentinel-1 and 2 imageries, it contains 30 fine land-cover types and achieves an overall accuracy of 83.16% and kappa coefficient of 0.789 using the globally distributed validation points.

The specific description can be found at the corresponding algorithm article. The GLC_FCS10 can be visually visited at zhangxiao-glcproj.users.earthengine.app/view/glcfcs102023maps