BEIJING (Xinhua) – A group of researchers has proposed a novel physics-based and cost-effective landslide displacement prediction framework, according to a research article recently published in journal Engineering Geology.
The prediction of landslide deformation is an important part of landslide early warning systems. Displacement prediction based on geotechnical in-situ monitoring performs well, while its high costs and spatial limitations hinder frequent use within large areas.
The researchers from China University of Geosciences, Peking University, Leibniz University Hannover and GFZ German Research Centre for Geosciences used the combination of Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR) and machine learning techniques to extract displacement time series for the landslide from satellite images to provide low-cost basic data for early warning and forecasting.
The application of the prediction method in the Three Gorges Reservoir area in China showed that the MT-InSAR can accurately monitor landslide deformation and machine learning algorithms can accurately establish the nonlinear relationship between the landslide deformation and its triggers.
By integrating the advantages of MT-InSAR and machine learning techniques, the proposed prediction framework, considering the physics principles behind landslide deformation, can predict landslide displacement cost-effectively within large areas, noted the research article.
