Abstract
Mapping landslides using automated methods is a challenging task, which is still largely done using human efforts. Today, the availability of high-resolution EO data products is increasing exponentially, and one of the targets is to exploit this data source for the rapid generation of landslide inventory. Conventional methods like pixel-based and object-based machine learning strategies have been studied extensively in the last decade. In addition, recent advances in CNN (convolutional neural network), a type of deep-learning method, has been widely successful in extracting information from images and have outperformed other conventional learning methods. In the last few years, there have been only a few attempts to adapt CNN for landslide mapping. In this study, we introduce a modified U-Net model for semantic segmentation of landslides at a regional scale from EO data using ResNet34 blocks for feature extraction. We also compare this with conventional pixel-based and object-based methods. The experiment was done in Douglas County, a study area selected in the south of Portland in Oregon, USA, and landslide inventory extracted from SLIDO (Statewide Landslide Information Database of Oregon) was considered as the ground truth. Landslide mapping is an imbalanced learning problem with very limited availability of training data. Our network was trained on a combination of focal Tversky loss and cross-entropy loss functions using augmented image tiles sampled from a selected training area. The deep-learning method was observed to have a better performance than the conventional methods with an MCC (Matthews correlation coefficient) score of 0.495 and a POD (probability of detection) rate of 0.72 .
Highlights
Landslides are defined as the gravity-driven movement of a mass of rock, debris, or earth down a slope [1]
To compare the performance of the tested algorithms, a summary of the prediction maps are calculated in the form of a confusion matrix, which includes the true positive, true negative, false positive (FP) and, false negative (FN) values
We approached landslide mapping using Convolutional Neural Networks (CNN) as a semantic segmentation task, which was lacking in previous works
Summary
Landslides are defined as the gravity-driven movement of a mass of rock, debris, or earth down a slope [1]. The World Bank has identified a total land area of 3.7 million square kilometers under risk of landslides, out of which 820 thousand square kilometers are high-risk zones [3]. This affects around 300 million people, which accounts for 5% of the world’s population. The slow-moving unstable slopes hold enough potential to damage or weaken engineering infrastructures like roads, buildings, and dams [5,6] These instabilities can develop into a rapid-moving catastrophic landslide affecting portions or even entire slopes, often triggered by external factors such as heavy rainfall, earthquakes, volcanic eruptions, and human activities [7]. A lot of work has already been done in studying the mechanics of mass-wasting processes [8] aimed at understanding its relationship with the conditioning factors [9] at identifying hazardous areas and determining the risks involved [10,11]
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.
