Temporal and Spatial Analysis of Deformation and Instability, and Trend Analysis of Step Deformation Landslide
Open Access
Abstract
This study focuses on step deformation landslides, conducting spatiotemporal analysis of landslide deformation and instability trends. First, the target landslide area is selected, and geological and precipitation data, along with historical displacement data from monitoring points, are collected. The slope single-change-point analysis method is then employed, combined with landslide profile data, to extract key features from the monitoring data. Next, Small BAseline Subset-Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology is applied to obtain satellite images of the study area. These images, together with the extracted data features, are used to draw the spatiotemporal baseline of the target landslide, completing the spatiotemporal analysis. Finally, a landslide prediction model is developed, and its prediction error is corrected using an Extreme Learning Machine (ELM) neural network. The refined prediction results serve as the basis for analyzing the landslide deformation coefficient, enabling the determination of the landslide instability trend. The experimental results show that step deformation landslides exhibit significant spatiotemporal variability and a short stability period throughout the year. The analytical methods designed in this study outperform traditional methods, providing more reliable results for predicting landslide instability trends.Keywords
Funding Information
- Special Project of Sichuan Provincial Bureau of Geology and Mineral Resources Exploration and Development (SCDZ-DH202508, 242102320009)
- Promotion Special Projects (Science and Technology Research) in Henan province (SCDZ-DH202508, 242102320009)
This publication has 19 references indexed in Scilit:
- Shear strain prediction of reservoir landslide based on FBG monitoring and bagging-MLP algorithmBulletin of Engineering Geology and the Environment, 2025
- Dynamic intelligent prediction approach for landslide displacement based on biological growth models and CNN-LSTMJournal of Mountain Science, 2025
- Whole Life Cycle Monitoring of Landslide Deep Deformation via Triboelectric NanogeneratorAdvanced Functional Materials, 2024
- A step-like landslide identification and prediction method based on trend speed ratioBulletin of Engineering Geology and the Environment, 2024
- Monitoring surface deformation with spaceborne radar interferometry in landslide complexes: insights from the Brienz/Brinzauls slope instability, Swiss AlpsLandslides, 2024
- Detection of slow‐moving landslides through automated monitoring of surface deformation using Sentinel‐2 satellite imageryEarth Surface Processes and Landforms, 2024
- Singular spectrum analysis-based hybrid PSO-GSA-SVR model for predicting displacement of step-like landslides: a case of Jiuxianping landslideActa Geotechnica, 2023
- Monitoring and prediction of landslide-related deformation based on the GCN-LSTM algorithm and SAR imageryNatural Hazards, 2023
- InterpolatiON of InSAR Time series for the dEtection of ground deforMatiOn eVEnts (ONtheMOVE): application to slow-moving landslidesLandslides, 2023
- Multitemporal relative landslide exposure and risk analysis for the sustainable development of rapidly growing citiesLandslides, 2023