Multitemporal Decomposition and Unsupervised Classification Analysis of Dual PolSAR Images

Synthetic aperture radar (SAR) is now proven to be a powerful ground monitoring tool. Over the last decade, SAR sensors have been developed that can detect multiple polarization states while maintaining phase information. These systems, called Polarimetric SAR (PolSAR), transmit and receive both vertically and horizontally polarized microwave signals. Optical data provides various information about the reflectance characteristics of targets with respect to spectral density with the help of electro-optical sensors, SAR data includes detailed information about polarization state and geometrical structure of natural and artificial objects, surface roughness and dielectric properties. In this study, the classification of polarimetric images produced by slice assembling from dual polarimetric multitemporal satellite images of C-band Sentinel-1A fit was preferred for ease of application of polarimetric decomposition analysis and unsupervised classification method due to the interpretability of polarimetric signatures. Within the scope of the study, we used PolSAR methods by applying the H-alpha decomposition algorithm to PolSAR images using the (Single Look Complex) SLC mode dual polarimetric images and the targets and methods using Sentinel-1A satellites 2014 and 2018 dual polarimetric multitemporal SAR images of the in the previously not tested region with the PolSAR classification. And also, polarimetric parameters are interpreted. Unsupervised classification was carried out to reveal changes in the field of work and to provide visual analysis. The overall classification accuracy as a result of classification is calculated as 88.5% for 2014 and 89.0% for 2018. Land changes in the urban and rural areas for 2014 and 2018 have been identified. The study also aimed to examine the capabilities of dual polarimetric C-band SAR data for terrestrial land cover classification. In the future study the effect of quad polarimetrik SAR and optical images used in different bands according on classification analysis will be investigated