Deformation Monitoring of Yuka Mining Area Based on Licsbas Using Velocity Neighborhood Spatial Algorithm Combined with T-Gcn

Abstract

Geological disaster risks associated with mining activities have become increasingly urgent. However, most existing methods solely evaluate the deformation of individual points in mining areas and do not evaluate the overall deformation of an entire working face, and decorrelation occurring in existing models can degrade interferometric results in time series InSAR measurements. To address these disadvantages, this study introduces a novel velocity–neighborhood spatial algorithm to accurately predict mining deformation trends and build upon the precise extraction of surface deformations from mining areas. Initially, surface deformation data from the Yuka mining area in Qinghai Province were obtained using the LiCSBAS method and transformed into a graphical structure. Subsequently, the T-GCN model was used to predict the deformation trends. The experimental results demonstrate that the T-GCN model improved upon the accuracy of traditional recurrent neural networks and machine learning algorithms by 4% with a 15% reduction in root mean square error, thus proving its substantive advantages in spatiotemporally related deformation trend predictions. The proposed method provides a more accurate and comprehensive scientific basis for monitoring and controlling geological disasters in mining areas as well as showcases the vast application prospects of the T-GCN model.

Keywords: Mining area monitoring, SAR, LiCSBAS, Deep learning, T-GCN