Application Of Neural Networks To Sea Ice Classification Using Polarimetric SAR Images

Author(s):  
R. Kwok ◽  
Y. Hara ◽  
R.G. Atkins ◽  
S.H. Yueh ◽  
R.T. Shin ◽  
...  
1995 ◽  
Vol 33 (3) ◽  
pp. 740-748 ◽  
Author(s):  
Y. Hara ◽  
R.G. Atkins ◽  
R.T. Shin ◽  
Jin Au Kong ◽  
S.H. Yueh ◽  
...  

2019 ◽  
Vol 16 (8) ◽  
pp. 1240-1244 ◽  
Author(s):  
Feng Gao ◽  
Xiao Wang ◽  
Yunhao Gao ◽  
Junyu Dong ◽  
Shengke Wang

2016 ◽  
Vol 10 (4) ◽  
pp. 1529-1545 ◽  
Author(s):  
Xi Zhang ◽  
Wolfgang Dierking ◽  
Jie Zhang ◽  
Junmin Meng ◽  
Haitao Lang

Abstract. In this paper we introduce a parameter for the retrieval of the thickness of undeformed first-year sea ice that is specifically adapted to compact polarimetric (CP) synthetic aperture radar (SAR) images. The parameter is denoted as the "CP ratio". In model simulations we investigated the sensitivity of the CP ratio to the dielectric constant, ice thickness, ice surface roughness, and radar incidence angle. From the results of the simulations we deduced optimal sea ice conditions and radar incidence angles for the ice thickness retrieval. C-band SAR data acquired over the Labrador Sea in circular transmit and linear receive (CTLR) mode were generated from RADARSAT-2 quad-polarization images. In comparison with results from helicopter-borne measurements, we tested different empirical equations for the retrieval of ice thickness. An exponential fit between the CP ratio and ice thickness provides the most reliable results. Based on a validation using other compact polarimetric SAR images from the same region, we found a root mean square (rms) error of 8 cm and a maximum correlation coefficient of 0.94 for the retrieval procedure when applying it to level ice between 0.1 and 0.8 m thick.


2015 ◽  
Vol 9 (5) ◽  
pp. 5445-5483
Author(s):  
X. Zhang ◽  
W. Dierking ◽  
J. Zhang ◽  
J. M. Meng ◽  
H. T. Lang

Abstract. In this paper we introduce a parameter for the retrieval of the thickness of undeformed first-year sea ice that is specifically adapted to compact polarimetric SAR images. The parameter is denoted as "CP-Ratio". In model simulations we investigated the sensitivity of CP-Ratio to the dielectric constant, thickness, surface roughness, and incidence angle. From the results of the simulations we deduced optimal conditions for the thickness retrieval. On the basis of C-band CTLR SAR data, which were generated from Radarsat-2 quad-polarization images acquired jointly with helicopter-borne sea ice thickness measurements in the region of the Sea of Labrador, we tested empirical equations for thickness retrieval. An exponential fit between CP-Ratio and ice thickness provides the most reliable results. Based on a validation using other compact polarimetric SAR images from the same region we found a root mean square (rms) error of 8 cm and a maximum correlation coefficient of 0.92 for the retrieval procedure when applying it on level ice of 0.9 m mean thickness.


Sign in / Sign up

Export Citation Format

Share Document