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.

Deep learning-based methods for the daily prediction of fishing vessel activity areas in the Japan Sea and East China Sea (25–40° N, 120–140° E) were investigated herein, using data obtained from Visible Infrared Imaging Radiometer Suite (VIIRS) boat detection (VBD). VBD grid images were created by aggregating fishing vessels’ position data into 64×64 grids, with the final input day’s distribution used as the baseline for evaluation. To suppress detection failures from clouds, the evaluation was limited to clear detections using quality flags (QFs). Indices were binarized using thresholds of 1, 5, and ≥10 fishing vessels, and F1 and intersection over union (IoU) metrics were applied to evaluate the models’ prediction performance for congested areas. Performance improvements obtained via encoder modifications were confirmed, with U-Net models using six-channel input DenseNet121 and ResNet50 showing high performance. The 6ch_densenet121 model achieved approx. 30% improvement in the average F1 and IoU values compared to the baseline, with 5%–10 % improvements for higher vessel-density areas. A novel Adaptive Multi-Temporal Integration Module (AMTIM) was developed to integrate temporal features including the year, month, day, lunar age, solar longitude, and tidal phase. In a six-channel ResNet50 model, the use of the AMTIM improved the average F1 from 0.383 to 0.393 and the average IoU from 0.237 to 0.245, demonstrating an approx. 3 % performance gain. When the AMTIM used only basic temporal information (i.e., year, month, day), the performance degraded, confirming the importance of domain-specific temporal features. Although it was developed for the prediction of fishing activity, the AMTIM’s general-purpose design enables applications to other domains that require non-spatial temporal information integration. The models successfully complemented the activity areas during cloud-interrupted observations, confirming their contribution to continuous fishing vessel monitoring.