Neighbor2Neighbor深層学習を用いた干渉SAR時系列地表変動の解析における誤差低減手法の開発

抄録

Interferometric synthetic aperture radar (InSAR) analysis is an effective way of observing surface displacement based on SAR data. SAR actively irradiates microwaves and InSAR analysis estimates surface displacement from changes in the phase of the backscattered signals. However, the accuracy of the estimated surface displacement is affected by certain error factors, such as the phase delay in the troposphere and the scattering of microwaves on the ground surface. In this study, we developed an error reduction method for time-series surface displacement by improving the Neighbor2Neighbor deep learning method. First, our proposed method was applied to synthetic data to examine the effectiveness of the method and determine the required number of SAR data. Next, InSAR analysis was conducted using ALOS-2/PALSAR-2 data obtained in the Kujukuri area in Chiba Prefecture, Japan, and the proposed noise reduction method was applied to the estimated time-series surface displacement. In the synthetic data analysis, both tropospheric and decorrelation noises were successfully mitigated by the proposed method. Our results further showed that error reduction was achieved with the same or higher accuracy than that achieved with conventional temporal filters when more than 30 SAR data were used. Our proposed error reduction method was also effective in the actual SAR data analysis, in which it was able to better identify the displacement areas of land subsidence that progresses over time.