Abstract: Remote sensing technology plays an important role in the field of geological disaster prevention and control. With the development of aerospace technology, more remote sensing data can be obtained and effectively applied to the identification of geological hazard bodies, especially in the identification of landslide hazards. Comprehensive use of InSAR and optical remote sensing data to identify geological hazards is a hot topic in recent research. The traditional recognition process relies entirely on the work experience of interpreters, with strong subjectivity and no fixed recognition logic to follow. Based on SBAS-InSAR and optical satellite imagery, this paper analyzes the process of landslide hazard identification, and constructs the Knowledge graph and identification extraction matrix model of landslide identification. Under the logic drive of the Knowledge graph, the regional spatial characteristics of landslide hazards identified by the combination of “optical remote sensing+InSAR” are analyzed, providing a reference implementation scheme with the significance of semi quantitative extraction of indicators for landslide wide area identification, and realizing the identification process of landslide hazards from completely subjective to semi quantitative. Experiments show that this method can provide reference for relevant research and practical engineering applications, and has certain application value.

Key words: landslide hazards, InSAR, optical imaging, knowledge graph, remote sensing recognition