An Improved Spatial Clustering Method for Automatic Detection of Active Geohazards in Lanzhou

Spaceborne interferometric synthetic aperture radar (InSAR) has been extensively employed to detect surface displacements. However, the automatic extraction of locations and boundaries of active geohazards from surface displacement data remains a significant research challenge. In this study, we propose an improved spatial clustering method to automatically detect active geohazards in Lanzhou City, Gansu Province, China. First, we applied the General Atmospheric Correction Online Service for InSAR (GACOS) assisted InSAR stacking technique to derive the annual surface deformation rate. Then, the C-index was employed to eliminate false deformation signals, and a spatial clustering method was used to delineate the boundaries of active geohazards efficiently. Subsequently, the geohazards were classified, and their spatial distribution characteristics were analyzed. Our results revealed that the annual surface deformation rates in Lanzhou city ranged from -176 mm/yr to 74 mm/yr. The combination of ascending- and descending-track SAR images increased the observable area from 86.3% (ascending only) and 93.4% (descending only) to 96.8%. Additionally, applying the C-index reduced misdetection probabilities by 14.4% and 10.9% for the ascending and descending tracks, respectively. Using the improved spatial clustering method, 775 active geohazards, including 331 active landslides and 444 land subsidence areas, were identified and mapped in Lanzhou City for the first time. Active landslides are predominantly located in the northern and southern hills of the urban area, while land subsidence mainly occurs in areas where hills have been excavated or flattened through land grading and leveling for urban development. The improved spatial clustering approach effectively and automatically extracts, classifies, and characterizes active geohazards, enabling rapid cataloging and providing essential data for geohazard management and risk assessment.