TY  - JOUR
T1  - Radarsat-1 Sar Surface Current Detection By Neural Network
AU - , Maged Marghany 
JO  - Asian Journal of Information Technology
VL  - 4
IS  - 2
SP  - 147
EP  - 151
PY  - 2005
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2005.147.151
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2005.147.151
KW  - 
AB  - This study introduces a new approach for utilizing the neural network for surface current simulation from RADARSAT-1 SAR image. The neural network input is a vector containing the values of the RADARSAT-1 SAR image intensity gradients. In this study, a single feed forward -propagation neural network was utilized to estimate the Doppler frequency shift in order to determine the surface current pattern along RADARSAT-1 SAR image. It is found that, the neural network outperformed conventional regression technique in modeling surface current velocity and their directions. The RMSE detected from NN model was 0.18 m/s. The reduction of the amount of the errors is due to good performance of regression model.
ER  -