The aims of this research were to map and analyze the risk of land subsidence in the Seoul Metropolitan Area, South Korea using satellite interferometric synthetic aperture radar (InSAR) time-series data, and three ensemble machine-learning models, Bagging, LogitBoost, and Multiclass Classifier. Of the types of infrastructure present in the Seoul Metropolitan Area, subway lines may be vulnerable to land subsidence. In this study, we analyzed Persistent Scatterer InSAR time-series data using the Stanford Method for Persistent Scatterers (StaMPS) algorithm to generate a deformation time-series map. Subsidence occurred at four locations, with a deformation rate that ranged from 6–12 mm/year. Subsidence inventory maps were prepared using deformation time-series data from Sentinel-1. Additionally, 10 potential subsidence-related factors were selected and subjected to Geographic Information System analysis. The relationship between each factor and subsidence occurrence was analyzed by using the frequency ratio. Land subsidence susceptibility maps were generated using Bagging, Multiclass Classifier, and LogitBoost models, and map validation was carried out using the area under the curve (AUC) method. Of the three models, Bagging produced the largest AUC (0.883), with LogitBoost and Multiclass Classifier producing AUCs of 0.871 and 0.856, respectively.

The availability of groundwater is of concern. The demand for groundwater in Korea increased by more than 100% during the period 1994–2014. This problem will increase with population growth. Thus, a reliable groundwater analysis model for regional scale studies is needed. This study used the geographical information system (GIS) data and machine learning to map groundwater potential in Gangneung-si, South Korea. A spatial correlation performed using the frequency ratio was applied to determine the relationships between groundwater productivity (transmissivity data from 285 wells) and various factors. This study used four topography factors, four hydrological factors, and three geological factors, along with the normalized difference wetness index and land use and soil type. Support vector regression (SVR) and metaheuristic optimization algorithms—namely, grey wolf optimization (GWO), and particle swarm optimization (PSO), were used in the construction of the groundwater potential map. Model validation based on the area under the receiver operating curve (AUC) was used to determine model accuracy. The AUC values of groundwater potential maps made using the SVR, SVR_GWO, and SVR_PSO algorithms were 0.803, 0.878, and 0.814, respectively. Thus, the application of optimization algorithms increased model accuracy compared to the standard SVR algorithm. The findings of this study improve our understanding of groundwater potential in a given area and could be useful for policymakers aiming to manage water resources in the future.

Despite the development of point-based interferometric synthetic aperture radar (InSAR) time-series methods, such as persistent scatterer interferometry (PSI), it remains difficult to identify reliable measurement points (MPs) in areas under vegetated cover. In this study, we developed a new algorithm, improved combined scatterers interferometry with optimized point scatterers (ICOPS), to monitor changes in surface deformation by combining persistent scatterers (PSs) and distributed scatterers (DSs). The algorithm was subsequently improved through the application of a machine learning process. A generalized likelihood ratio test (GLRT) was applied to identify statistically homogeneous pixels suitable for a small SAR dataset. A machine learning-based optimization process was used to overcome the increase in MPs after the combined scatterers interferometry (CSI) process. The MP optimization process used the support vector regression (SVR) algorithm to find the optimal point from all MPs in the dataset. To improve the reliability of the MP surface deformation mapping after optimization, the optimized hot-spot analysis (OHSA) method was applied to obtain spatially clustered MPs; this was possible despite a low deformation identification rate. To demonstrate the effectiveness of the ICOPS method, we applied this approach to Yellowstone Lake in the USA using 95 SAR images from the Sentinel-1 satellite that was taken during the period of 2017–2020. The CSI method produced an increase in MP density, especially in areas not covered by PSI, which indicated its ability to detect deformations in mountainous areas. Comparisons with GPS data and traditional methods produced promising results with an accuracy of 1 cm/year in terms of the root mean square error (RMSE). The optimization process in CSI also had the advantage of retrieving helpful information in the MP dataset and increased the accuracy of CSI by 12%. Deformation mapping using the optimized results provided new insights regarding the spatial clustering of surface deformation in MPs. This could provide the foundation for developing a posttime-series optimization process based on point scatter as a surface change detection tool.

Floods in Pekalongan, Indonesia, often occur due to river water overflowing during heavy monsoon rain. Simultaneously, the northern coastal area of Pekalongan, located adjacent to the Java Sea, has been affected by coastal floods due to sea level rise. The flood conditions in this area were exacerbated by land subsidence, leading to coastal inundation. Monitoring land subsidence in Pekalongan has become essential in predicting other possible land subsidence occurrence areas and mitigating the possible hazards caused by land subsidence. The analysis of land subsidence has been much easier since the introduction of radar satellites. In this study, 124 synthetic aperture radar (SAR) datasets from the Sentinel-1 radar satellite between 2017 and 2022 in descending tracks were used. The data were processed through a time-series interferometry SAR (InSAR) method based on the improved combined scatterers interferometry with optimized point scatterers (ICOPS) algorithm to provide accurate measurements over large areas by improving the selection of measurement points from persistent scatterer (PS) and distributed scatterer (DS) points using a deep learning algorithm based on a convolutional neural network (CNN), and the resulting optimized measurement points were then spatially clustered using optimized hot spot analysis (OHSA) to estimate significant points statistically and define them as hot spot points. The results of time-series deformation in Pekalongan were compared with the GPS station measurements. From the comparison, a good correlation in terms of deformation patterns between time-series InSAR and GPS measurements was observed. Our study revealed that land subsidence in Pekalongan has occurred mostly in settlement areas under the young alluvium soil, which cannot support many buildings’ maximum compression. Another cause of land subsidence in Pekalongan is excessive groundwater extraction in settlement areas. Thus, compaction in the aquifer areas may occur as a result of the reduced effective stress of the pore pressure. Further analysis of this study would involve monitoring groundwater activity using data from the GRACE satellite and comparing them with weather station data. The analysis of the two datasets aims to understand the relationships between groundwater storage data and the monthly precipitation in Pekalongan. Finally, the potential outcomes of land subsidence in Pekalongan will be assessed using the geographic information system (GIS) method based on susceptibility mapping.

An interesting liquefaction event happened following the 5.6 Mw Pohang earthquake on November 15, 2017. Liquefaction affects soil density as a result of earthquake vibrations, causing water to ascend and combine with solid soil. In general, this effect results from increasing water pressure in the buried lower layer. Remote sensing data, particularly those obtained with differential interferometric synthetic aperture radar (DInSAR), can be utilized to assess surface changes and soil moisture levels. This analysis utilizes Sentinel-1 C-band data from 2017 to 2020. Furthermore, the biased time-series identification presented to analyze the anomaly may be present in this study. In addition, optical satellite data were used to estimate changes in water content and soil moisture following the Pohang earthquake. A combination of spectral bands sensitive to changes in water content was used to identify anomalies following an earthquake based on Sentinel-2 and Landsat-8 data. Based on the spatial analysis, optical images may detect changes in water content with a spatial accuracy of 60-80% when compared to field data. Moreover, the liquefaction susceptibility map has been generated using a hybrid dense convolutional neural network architecture and swarm-based optimization algorithm. As a result, the susceptibility model performance was conducted using k-fold cross-correlation with an AUC value of 0.75-0.86. However, this research was the initial effort to determine the potential of liquefaction in the future based on the 2017 Pohang earthquake, and the results can improve our understanding of this phenomenon. compression.