Deformation monitoring and prediction for residential areas in the Panji mining area based on an InSAR time series analysis and the GM-SVR model

Abstract

Underground coal mining activities often cause ground subsidence and damage to surface construction, which seriously threatens the lives and property of residents in mining areas. In this paper, the deformation of the Yang Juzhuang village, which is a residential area in the Huainan mining area (China), was monitored through an interferometric synthetic aperture radar (InSAR) time series analysis. The vertical displacements were detected using thirteen Sentinel-1A images that were acquired between December 2016 and May 2017. The validity and applicability of the method are verified by comparing the acquired images with the GPS measurement results. Because of the deformation characteristics of the mining area, a prediction model that is combined with a grey support vector machine regression (GM-SVR) is proposed, and the practical effects of the model are verified using the deformation monitoring results of the study area. The combination of this model and SBAS-InSAR provides rapid dynamic monitoring and enables the issuance of disaster warnings in the region.

Keywords

• sbas-insar
• disaster warning
• settlement prediction
• sentinel-1a
• gps