Abstract
With the increased availability of high-resolution digital terrain models (HRDTM) generated using airborne light detection and ranging (LiDAR), new opportunities for improved mapping of geohazards such as landslides arise. While the visual interpretation of LiDAR, HRDTM hillshades is a widely used approach, the automatic detection of landslides is promising to significantly speed up the compilation of inventories. Previous studies on automatic landslide detection often used a combination of optical imagery and geomorphometric data, and were implemented in commercial software. The objective of this study was to investigate the potential of open source software for automated landslide detection solely based on HRDTM-derived data in a study area in Burgenland, Austria. We implemented a geographic object-based image analysis (GEOBIA) consisting of (1) the calculation of land-surface variables, textural features and shape metrics, (2) the automated optimization of segmentation scale parameters, (3) region-growing segmentation of the landscape, (4) the supervised classification of landslide parts (scarp and body) using support vector machines (SVM), and (5) an assessment of the overall classification performance using a landslide inventory. We used the free and open source data-analysis environment R and its coupled geographic information system (GIS) software for the analysis; our code is included in the Supplementary Materials. The developed approach achieved a good performance (κ = 0.42) in the identification of landslides.
Highlights
We examined the potential of open source software to conduct geographic object-based image analysis (GEOBIA) for landslide detection using solely high-resolution digital terrain models (HRDTM)-derived variables
After visual inspection of the segmentation results with the locally optimal scales, we decided to use the threshold of 0.075 for the final segmentation of the candidate scarp area, and the Level of Generalisation of 3.25 for the final segmentation of the candidate body area. The reason for this selection was based on the desired object size: While for the candidate scarp area, a local optimum with a small threshold resulted in more suitably sized objects, for the candidate body area a relatively large value of Level of Generalisation resulted in adequately sized objects
Inventories are the basis for any landslide analysis, but their digitization by human experts is a time-consuming process [3] and is subjective to the opinion of the creator [5]
Summary
With the ongoing environmental change and the potential exposure of humans to landslides, the identification of areas susceptible to landsliding has become increasingly important for risk reduction and spatial planning [1,2]. The quality of inventories is of critical importance for the explanatory power and unbiasedness of the landslide susceptibility models and their predictions [4], but their compilation is time-consuming and hinges on the subjective assessment of experts [3,5]. The traditional creation of landslide inventories by visual interpretation of aerial photographs and extensive fieldwork has been increasingly supported by or even replaced with the expert-based visual detection or (semi- or fully) automated landslide detection using light detection and ranging (LiDAR) data [3,6,7]. The increasing availability of airborne LiDAR-derived high-resolution digital terrain models (HRDTM) creates the opportunity to detect landslides even within forests, where imagery from passive optical sensors is of limited utility [7], or in remote, difficult-to-access areas such as high mountains [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
