Fuzzy Geospatial Object-Based Membership Function Downscaling

The area-to-point kriging method (ATPK) is an important technology of downscaling without auxiliary information in remote sensing. However, it uses a constant semivariogram to downscale geospatial variables, which ignores the spatial heterogeneity between objects. To deal with this kind heterogeneity, study proposes fuzzy object-based ATPK method, mainly consists three steps: extraction objects, estimation semivariograms for each object, and object by corresponding semivariogram. Two groups membership functions acquired from Worldview-2 Sentinel-2 are used test proposed approach. Six classic algorithms compared, results two experiments show better performance than classical methods.