Land use and land cover classification using co-polarimetric PAZ SAR images
Suggested elective courses: Radar remote sensing, advanced image analysis
No fieldwork is included/required
Spanish PAZ, which was launched in February 2018, offers co-polarimetric (with HH and VV channel) SAR images with X-band and (down to) 11 days repeat cycle. By analyzing the backscatterer characteristics and applying polarimetric decomposition, the radar scatterers from multi-temporal SAR images can be classified according to scattering mechanisms (mainly including surface, volume and dihedral scattering mechanism) and land use/land cover classification products can be obtained. This study aims at producing a reliable classification map and classification dynamic map using PAZ co-pol SAR data.
This study will utilize and compare several polarimetric decomposition methods to generate reliable classification maps. The main objective is to demonstrate and assess the applicability of land use and land cover classification using PAZ co-pol SAR imagery, and determine the most suitable (decomposition) method for the test site. The test site will be in the north part of the Netherlands, with the spatial extent of ~750km2. 30 PAZ SAR images will be available for this study. The optical images, such as Landsat-8 and Sentinel-2 can be used for result comparison.
Ling Chang and Alfred Stein (2021). Exploring PAZ co-polarimetric SAR data for surface movement mapping and scattering characterization. International Journal of Applied Earth Observation and Geoinformation 96.