Abstract
In recent years, due to the obvious ground settlement and other phenomena of the Yinxi Industrial Park in Baiyin, it has brought many hidden dangers to the local development, it is of great practical significance to monitor the deformation of the area for a long time series. The ground deformation field of Yinxi Industrial Park from June 2018 to April 2021 was obtained by processing Sentinel-1A data using SBAS technology, and the high coherence point D1 was predicted and analyzed by BP neural network. The results show that subsidence occurs in several places in the Yinxi Industrial Park, and the average annual subsidence rate ranges from -19.28 mm to 5.08 mm, the areas of severe settlement have a clear geographical distribution, mainly concentrated in road and building areas, other areas have a more stable ground base; the mean square error in the BP neural network prediction result is 2.56 mm, and the average relative error is 6.06%, which is a high prediction accuracy. The predicted cumulative settlement value at point D1 in 2023 is 45 mm, and there is a tendency for the settlement to intensify. The prediction results are of great significance for the early identification and prevention of ground settlement in the study area.
Highlights
Ground settlement is a common geological problem in social and economic development [1,2], mainly caused by natural and man-made factors that lead to local or regional subsidence phenomena, usually occurring as a result of foundation instability, building damage and other geological disasters, and is one of the important obstacles to the health and sustainable development of the region [3]
For early identification and prevention of the study area, 1100 PS points were selected from the results obtained with SBAS technique, the first 1000 PS point settlement values were randomly selected as training samples and the last 100 PS point settlement values were used as test samples, the 33 period settlement values from June 14, 2018 to March 6, 2021 were used as the input layer and the settlement values on April 11, 2021 were used as the output layer, the sample data are normalized and prediction analysis is performed based on BP neural network model
The prediction of the cumulative settlement value at point D1 using BP neural network is shown in Figure 9, and the results show that the settlement value at point D1 will exceed 45 mm in 2023, and the cumulative settlement will further increase under the action of external loads such as vehicles because the point is located on the highway
Summary
Ground settlement is a common geological problem in social and economic development [1,2], mainly caused by natural and man-made factors that lead to local or regional subsidence phenomena, usually occurring as a result of foundation instability, building damage and other geological disasters, and is one of the important obstacles to the health and sustainable development of the region [3]. Zhao Fumeng et al. American Journal of Civil Engineering 2021; 9(5): 167-172 used SBAS technology based on sentinel data for early identification of geological hazards in the Ghazi Valley of the China-Pakistan Highway and extracted regional deformation information of geological hazards [7], and Pan Guangyong et al applied SBAS technology to mine subsidence monitoring and effectively obtained the annual average subsidence rate and cumulative subsidence in the mine area [8]. American Journal of Civil Engineering 2021; 9(5): 167-172 used SBAS technology based on sentinel data for early identification of geological hazards in the Ghazi Valley of the China-Pakistan Highway and extracted regional deformation information of geological hazards [7], and Pan Guangyong et al applied SBAS technology to mine subsidence monitoring and effectively obtained the annual average subsidence rate and cumulative subsidence in the mine area [8] These studies show that it is feasible to apply SBAS technology to ground subsidence monitoring and identification on a large scale; there are fewer studies that combine different SBAS technologies with BP neural network models. We use SBAS technology to process and analyze 34 scenes of sentinel-1A data during the period from July 2018 to November 2021 in Yinxi Industrial Park, and predict the settlement points in the study area by BP neural network, in order to provide data support for early subsidence hazard identification and healthy and sustainable development in Yinxi Industrial Park
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
