Automatic Identification and Assessment of Potential Geohazards in a Wide Area Based on Multisource Remote Sensing and Deep Learning

Wide-area monitoring and accurate assessment of potential geohazards (PGHs) based on remote sensing will provide a crucial foundation for geohazard prevention and mitigation. Current remote sensing methods for PGH identification and evaluation require extensive manual effort and lack intelligence throughout the process. To effectively integrate multisource remote sensing data, we propose an automated method for identifying and assessing PGHs across a wide area. This approach integrates InSAR deformation, high-resolution optical remote sensing, terrain, and vector data of ground features to enable automated delineation of unstable zones, automatic identification of potentially threatened objects (PTOs), automatic screening of PGHs, and risk assessment. The proposed method is tested in the Hequ–Baode–Pianguan (HBP) region of Shanxi province. Using the DS-InSAR technique, we process 94 Sentinel-1 SAR images covering the HBP region from 2020 to 2024 to estimate surface stability. We automatically detect the boundaries of 161 active deformation areas (ADAs) in HBP. A deep learning model based on DeepLabV3+ processes optical remote sensing images of the study area at 0.5 m resolution to automatically identify all PTOs. By integrating terrain data and spatial relationships among PTOs and ADAs, we develop an algorithmic model to identify 90 PGHs and classify them into external-threat, internal-threat, and internal-external-threat geohazard zones. Finally, a risk matrix is created for an automatic geohazard risk assessment, producing results for all PGHs in the study area. This developed method will support wide-area screening and prioritization of potential geohazards on the Loess Plateau and improve PGH investigation capabilities.