Automatic landslide mapping from satellite imagery with a topography-driven thresholding algorithm

• Published in: PeerJ preprints
• Main Authors: Alvioli, Massimiliano, Mondini, Alessandro C, Fiorucci, Federica, Cardinali, Mauro, Marchesini, Ivan
• Format: Journal Article
• Language: English
• Published: San Diego PeerJ, Inc 12.11.2018
• Subjects: Classification; Landslides; Landslides & mudslides; Mapping; Topography
• ISSN: 2167-9843
• DOI: 10.7287/peerj.preprints.27067v2

We present an improvement of image classification for landslide mapping by “thresholding”, using topographic information to determine multiple thresholds. We devised a two-steps procedure for automatic classification into landslide or no landslide categories of a change-detection map obtained from satellite imagery. Requirements of the proposed procedure are knowledge of the occurrence of a landslide event, availability of a pre- and postevent pseudo-stereo image pair and a digital elevation model. The novel feature of the approach is represented by the use of slope units as topographic-aware subsets of the scene within which we apply a multiple thresholding method to classify a landslide class membership tuned on the sole landslide spectral response. The method is fully automatic after site-dependent operations, required only once, are performed, and exhibits improved classification performance with limited training requirements. Our automatic procedure is a step forward towards systematic acquisition of landslide events and real-time landslide mapping from satellite imagery.