“…Landslides are a major concern in regions with mountainous terrain, as they directly impact human lives and infrastructures 1 . Landslide events are often triggered by earthquakes, extreme meteorological occurrences, or anthropogenic activities.…”
Rapid mapping of event landslides is crucial to identify the areas affected by damages as well as for effective disaster response. Traditionally, such maps are generated with visual interpretation of remote sensing imagery (manned/unmanned airborne systems or spaceborne sensors) and/or using pixel-based and object-based methods exploiting data-intensive machine learning algorithms. Recent works have explored the use of convolutional neural networks (CNN), a deep learning algorithm, for mapping landslides from remote sensing data. These methods follow a standard supervised learning workflow that involves training a model using a landslide inventory covering a relatively small area. The trained model is then used to predict landslides in the surrounding regions. Here, we propose a new strategy, i.e., a progressive CNN training relying on combined inventories to build a generalized model that can be applied directly to a new, unexplored area. We first prove the effectiveness of CNNs by training and validating on event landslides inventories in four regions after earthquakes and/or extreme meteorological events. Next, we use the trained CNNs to map landslides triggered by new events spread across different geographic regions. We found that CNNs trained on a combination of inventories have a better generalization performance, with a bias towards high precision and low recall scores. In our tests, the combined training model achieved the highest (Matthews correlation coefficient) MCC score of 0.69 when mapping landslides in new unseen regions. The mapping was done on images from different optical sensors, resampled to a spatial resolution of 6 m, 10 m, and 30 m. Despite a slightly reduced performance, the main advantage of combined training is to overcome the requirement of a local inventory for training a new deep learning model. This implementation can facilitate automated pipelines providing fast response for the generation of landslide maps in the post-disaster phase. In this study, the study areas were selected from seismically active zones with a high hydrological hazard distribution and vegetation coverage. Hence, future works should also include regions from less vegetated geographic locations.
“…Landslides are a major concern in regions with mountainous terrain, as they directly impact human lives and infrastructures 1 . Landslide events are often triggered by earthquakes, extreme meteorological occurrences, or anthropogenic activities.…”
Rapid mapping of event landslides is crucial to identify the areas affected by damages as well as for effective disaster response. Traditionally, such maps are generated with visual interpretation of remote sensing imagery (manned/unmanned airborne systems or spaceborne sensors) and/or using pixel-based and object-based methods exploiting data-intensive machine learning algorithms. Recent works have explored the use of convolutional neural networks (CNN), a deep learning algorithm, for mapping landslides from remote sensing data. These methods follow a standard supervised learning workflow that involves training a model using a landslide inventory covering a relatively small area. The trained model is then used to predict landslides in the surrounding regions. Here, we propose a new strategy, i.e., a progressive CNN training relying on combined inventories to build a generalized model that can be applied directly to a new, unexplored area. We first prove the effectiveness of CNNs by training and validating on event landslides inventories in four regions after earthquakes and/or extreme meteorological events. Next, we use the trained CNNs to map landslides triggered by new events spread across different geographic regions. We found that CNNs trained on a combination of inventories have a better generalization performance, with a bias towards high precision and low recall scores. In our tests, the combined training model achieved the highest (Matthews correlation coefficient) MCC score of 0.69 when mapping landslides in new unseen regions. The mapping was done on images from different optical sensors, resampled to a spatial resolution of 6 m, 10 m, and 30 m. Despite a slightly reduced performance, the main advantage of combined training is to overcome the requirement of a local inventory for training a new deep learning model. This implementation can facilitate automated pipelines providing fast response for the generation of landslide maps in the post-disaster phase. In this study, the study areas were selected from seismically active zones with a high hydrological hazard distribution and vegetation coverage. Hence, future works should also include regions from less vegetated geographic locations.
“…Landslides are defined as the gravity-driven movement of a mass of rock, debris, or earth down a slope [1]. A sudden slope failure event can be a significant source of economic losses and fatalities when it affects areas of human influence [2]. 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].…”
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 .
“…Recently, several studies have highlighted the importance of these secondary effects on damage and loss of human life (e.g. Konovalov et al, 2019;Nowicki Jessee et al, 2020;Turner, 2018). Generally, landslide phenomena play an important role in the landscape evolution, occurring in relation to peculiar morphological, geological, and climatic characteristics, and to destabilizing effects induced by human and seismic activity (Bozzano et al, 2020;Calista et al, 2019;Carabella et al, 2019;Martino et al, 2020) and represent a serious hazard worldwide and in Italy (Aleotti & Chowdhury, 1999;Aringoli et al, 2010;Dramis et al, 2001;Farabollini et al, 1995;Glade et al, 2012;Marsala et al, 2019;Peruccacci et al, 2017;Quesada-Román et al, 2019;Tanyaş et al, 2017).…”
In this paper, a geomorphological map of Pescara del Tronto area (Sibillini Mts, Marche Region) is presented. The work focuses on the geomorphological analysis performed in a zone strongly struck by the 2016-2017 seismic sequence of Central Apennines. The geomorphological map (1:7,500 scale) was obtained through an integrated approach that incorporates geologicalgeomorphological field mapping and geomorphological profile drawing, supported by airphoto interpretation and GIS analysis. The main purpose of the work is to describe a geomorphological approach for representing and mapping the evidence of several debris flows and landslides recognized in the framework of seismic microzonation (SM) activities. Finally, in order to elevate geomorphological maps into effective tools for land management and risk reduction, it could provide a scientific and methodological basis to demonstrate that accurate mapping provides important information, readily available for local administrations and decision-makers, for the implementation of sustainable territorial planning and loss-reduction measures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.