Search

Rapid simulation of land subsidence can provide an effective means of facilitating its management and control. This paper innovatively introduced a back-propagation (BP) neural network subsidence simulation model which was optimized by the sparrow search algorithm (SSA), hereinafter referred to as the SSA-BP model, to simulate land subsidence in Tongzhou District, Beijing. First, based on the time series interferometric synthetic aperture radar (InSAR) monitoring, different technologies such as spatial analysis, Google Earth Engine (GEE), and machine learning were utilized together with a variety of multi-source spatial data, including groundwater level, compressible layer thickness, Visible Infrared Imager Radiometer Suite (VIIRS) nighttime light images, and the OpenStreetMap (OSM) road distribution. Furthermore, we determined the optimal grid scale for land subsidence research and worked out a multifactor-driven SSA-BP land subsidence simulation model for which sensitivity analysis was performed with great care. Main conclusions: (1) From November 2010 to January 2020, the average annual surface displacement rate in Beijing's subcentre, Tongzhou, ranged from −133.9 to +3.9 mm/year. (2) Our SSA-BP land subsidence simulation model allows for a relatively high overall accuracy. The average root mean square error (RMSE) is 5.00 mm/year, the average mean absolute error (MAE) is 3.80 mm/year, and the average coefficient of determination (R2) is 0.83. (3) Sensitivity analysis shows that the SSA-BP model driven by multiple factors has a far better simulation performance than the model driven by any single weighting factor, and displays the highest sensitivity to the groundwater level factor among all the weighting factors. In terms of subdividing the study area, our SSA-BP land subsidence model runs with multifunctional zones displayed a higher accuracy than that without. This paper made use of a machine learning model to simulate land subsidence in Beijing's Tongzhou District and explored the sensitivity of different factors to land subsidence, which is helpful for its scientific prevention. [ABSTRACT FROM AUTHOR]

Land subsidence threatens the stable operation of urban rail transit, including subways. Obtaining deformation information during the entire life-cycle of a subway becomes a necessary means to guarantee urban safety. Restricted by sensor life and cost, the single-sensor Multi-temporal Interferometric Synthetic Aperture Radar (MTI) technology has been unable to meet the needs of long-term sequence, high-resolution deformation monitoring, especially of linear objects. The multi-sensor MTI time-series fusion (MMTI-TSF) techniques has been proposed to solve this problem, but rarely mentioned. In this paper, an improved MMTI-TSF is systematically explained and its limitations are discussed. Taking the Beijing Subway Network (BSN) as a case study, through cross-validation and timing verification, we find that the improved MMTI-TSF results have higher accuracy (R2 of 98% and, Root Mean Squared Error (RMSE) of 4mm), and compared with 38 leveling points, the fitting effect of the time series is good. We analyzed the characteristics of deformation along the BSN over a 15-year periods. The results suggest that there is a higher risk of instability in the eastern section of Beijing Subway Line 6 (L6). The land subsidence characteristics along the subway lines are related to its position from the subsidence center, and the edge of the subsidence center presents a segmented feature. [ABSTRACT FROM AUTHOR]