Explore the vast range of titles available.

Convolution neural network (CNN) is an effective and popular deep learning method which automatically learns complicated non-linear mapping from original inputs to given labels or ground truth through a series of convolutional layers. This study focuses on detecting landslides from high-resolution optical satellite images using CNN-based methods, providing opportunities for recognizing latent landslides and updating large-scale landslide inventory with high accuracy and time efficiency. Considering the variety of landslides and complicated backgrounds, attention mechanisms originated from the human visual system are developed for boosting the CNN to extract more distinctive feature representations of landslides from backgrounds. As deep learning needs a large number of labeled data to train a learning model, we manually prepared a landslide dataset which is located in the Bijie city, China. In the dataset, 770 landslides, including rock falls, rock slides, and a few debris slides, were interpreted by geologists from the satellite images and digital elevation model (DEM) data and further checked by fieldwork. The landslide data was separated into a training set that trains the attention boosted CNN model and a testing set that evaluates the performance of the model with a ratio of 2:1. The experimental results showed that the best F1-score of landslide detection reached 96.62%. The results also proved that the performance of our spatial-channel attention mechanism was fairly over other recent attention mechanisms. Additionally, the effectiveness of predicting new potential landslides with high efficiency based on our dataset is demonstrated.

Landslides are catastrophic natural hazards that often lead to loss of life, property damage, and economic disruption. Image-based landslide investigations are crucial for determining landslide susceptibility and risk. In practice, satellite images have been widely utilized for such investigations; however, they still require significant labor and time resources. In this study, we propose an image-based two-phase data-driven framework for detecting and segmenting landslide regions using satellite images. In phase I, an object detection algorithm, Faster-RCNN, is trained to detect the landslide location within the large-scale satellite images. The bounding boxes of each landslide location are proposed and visualized. In phase II, we crop the satellite images into small images using the location information of the bounding boxes. Next, we use a boundary detection algorithm to identify the boundary information of each detected loess landslide to strengthen the segmentation performance. Finally, we improve the architecture of the segmentation U-Net by integrating additional inception blocks with dilation to enhance the landslide segmentation performance. A total of 150 local loess landslide occurrences in northern China are selected as our case study to validate the effectiveness, efficiency, and universality of the proposed two-phase framework. Segmentation of loess landslides is considered a challenging task due to the intrinsic nature of vague boundary information. The proposed framework is compared with the conventional U-Net and other recent benchmarking landslide segmentation algorithms. Computational results indicate that the proposed framework produces more accurate segmentation of loess landslides compared with the other tested benchmarking algorithms.

Using deep learning-based object detection algorithms for landslide hazards detection is very popular and effective. However, most existing algorithms are designed for landslides in a specific geographical range. This paper constructs a set of landslide detection models YOLOX-Pro, based on the improved YOLOX (You Only Look Once) target detection model to address the poor detection of complex mixed landslides. Wherein the VariFocal is used to replace the binary cross entropy in the original classification loss function to solve the uneven distribution of landslide samples and improve the detection recall; the coordinate attention (CA) mechanism is added to enhance the detection accuracy. Firstly, 1200 historical landslide optical remote sensing images in thirty-eight areas of China were extracted from Google Earth to create a mixed sample set for landslide detection. Next, the three attention mechanisms were compared to form the YOLOX-Pro model. Then, we tested the performance of YOLOX-Pro by comparing it with four models: YOLOX, YOLOv5, Faster R-CNN, and Single Shot MultiBox Detector (SSD). The results show that the YOLOX-Pro(m) has significantly improved the detection accuracy of complex and small landslides than the other models, with an average precision (AP0.75) of 51.5%, APsmall of 36.50%, and ARsmall of 49.50%. In addition, optical remote sensing images of a 12.32 km2 group-occurring landslides area located in Mibei village, Longchuan County, Guangdong, China, and 750 Unmanned Aerial Vehicle (UAV) images collected from the Internet were also used for landslide detection. The research results proved that the proposed method has strong generalization and good detection performance for many types of landslides, which provide a technical reference for the broad application of landslide detection using UAV.

Landslide disasters occur frequently in the mountainous areas in southwest China, which pose serious threats to the local residents. Interferometry Synthetic Aperture Radar (InSAR) provides us the ability to identify active slopes as potential landslides in vast mountainous areas, to help prevent and mitigate the disasters. Quickly and accurately identifying potential landslides based on massive SAR data is of great significance. Taking the national highway near Wenchuan County, China, as study area, this paper used a Stacking-InSAR method to quickly and qualitatively identify potential landslides based on a total of 40 Sentinel SAR images acquired from November 2017 to March 2019. As a result, 72 active slopes were successfully detected as potential landslides. By comparing the results from Stacking-InSAR with the results from the traditional SBAS-InSAR (Small Baselines Subset) time series method, it was found that the two methods had a high consistency, with 81.7% potential landslides identified by both of the two methods. A detailed comparison on the detection differences was performed, revealing that Stacking-InSAR, compared to SBAS-InSAR may miss a few active slopes with small spatial scales, small displacement levels and the ones affected by the atmosphere, while it has good performance on poor-coherence regions, with the advantages of low technical requirements and low computation labor. The Stacking-InSAR method would be a fast and powerful method to qualitatively and effectively identify potential landslides in vast mountainous areas, with a comprehensive understanding of its specialty and limitations.

Two successive landslides within a month started in October 11, 2018, and dammed twice the Jinsha River at the border between Sichuan Province and Tibet in China. Both events had potential to cause catastrophic flooding that would have disrupted lives of millions and induced significant economic losses. Fortunately, prompt action by local authorities supported by the deployment of a real-time landslide early warning system allowed for quick and safe construction of a spillway to drain the dammed lake. It averted the worst scenario without loss of life and property at least one order of magnitude less to what would have been observed without quick intervention. Particularly, the early warning system was able to predict the second large-scale slope failure 24 h in advance, along with minor rock falls during the spillway construction, avoiding false alerts. This paper presents the main characteristics of both slope collapses and damming processes, and introduces the successful landslide early warning system. Furthermore, we found that the slope endured cumulative creeping displacements of > 40 m in the past decade before the first event. Twenty-five meter displacement occurred in the year immediately before. The deformation was measured by the visual interpretation of multitemporal satellite images, which agrees with the interferometry synthetic aperture radar (InSAR) measurement. If these had been done before the emergency, economic losses could have been reduced further. Therefore, our findings strengthen the case for the deployment of systematic monitoring of potential landslide sites by integrating earth observation methods (i.e., multitemporal satellite or UAV images) and in situ monitoring system as a way to reduce risk. It is expected that this success story can be replicated worldwide, contributing to make our society more resilient to landslide events.

On 18 November 2017, a magnitude Ms. 6.9 (Mw 6.4) earthquake struck Nyingchi, Tibet Autonomous Region, China, which is located in the famous Grand Canyon region of the Yarlung Zangbo River in the eastern Himalayas, Tibet. The Nyingchi event was a thrusting event, with a focal depth of 12 km at 29.87° N and 95.02° E. According to emergency investigations and remote sensing, the Nyingchi event triggered at least 1820 co-seismic landslides. The landslides mainly occurred in the Grand Canyon region within an area of 527 km2 (the inner area of Namcha Barwa tectonic node). The landslide distribution characterises an obvious hanging wall effect and is classified as “small concentration region and large landslide distribution area”. The failure patterns mainly consist of rock falls, rock avalanches, and deposit failures. One co-seismic landslide partially blocked the Yarlung Zangbo River, and the barrier lake remained. Different influencing factors, such as the seismic fault, river, slope aspect, slope angle, rocks, and elevation, have different influences on landslide occurrences, and the co-seismic landslides in the hanging wall area and footwall area present obviously different characteristics. Additionally, the post-earthquake effect impacted the recent Sedongpu landslide.

Landslides are geological disasters that can cause great damage to natural and social environments. Landslide hazard assessments are crucial for disaster prevention and mitigation. Conventional regional landslide hazard assessment results are static and do not take into account the dynamic changes in landslides; thus, areas with landslides that have been treated and stabilized are often still identified as high-risk areas. Therefore, a new hazard assessment method is proposed in this paper that combines the deformation rate results obtained by interferometric synthetic aperture radar (InSAR) with the results of conventional hazard assessments to obtain the hazard assessment level while considering the deformation factor of the study area, with Zhouqu, Gansu Province, selected as the case study. First, to obtain the latest landslide inventory map of Zhouqu, the hazard assessment results of the study area were obtained based on a neural network and statistical analysis, and an innovative combination of the deformation rate results of the steepest slope direction from the ascending and descending data were obtained by InSAR technology. Finally, the hazard assessment level considering the deformation factor of Zhouqu was obtained. The method proposed in this paper allows for a near-term hazard assessment of the study area, which in turn enables dynamic regional landslide hazard assessments and improves the efficiency of authorities when conducting high-risk-area identification and management.

Increasingly frequent glacier-rock avalanches (GRAs) – events triggered by the detachment of both glacier and rock materials – have occurred in recent years in the Sedongpu gully in the eastern Himalayan syntaxis, blocking the course of the Yarlung Zangbo River repeatedly. To identify spatio-temporal patterns and influencing factors of these GRAs, we analyzed remote sensing images and produced high-resolution digital surface models. At least eight GRAs, originating from the same source areas, have occurred in the past decades: one in 1974, one in 2014, and six between 2017 and 2018. The GRAs that occurred since 2014 were responsible for the loss of > 70 Mm3 of glacier and rock and > 150 Mm3 of moraine deposits and increased the elevation of the basin outlet by 60–120 m. Climate change-induced glacier retreat, steep topography, and a recent strong earthquake were found to be related to the occurrence of the recent GRAs, which resulted in the formation of a knickpoint in the Yarlung Zangbo River.

Regional landslide identification is important for the risk management of landslide hazards. The traditional methods of regional landslide identification were mainly conducted by a human being. In previous studies, automatic landslide recognition mainly focused on new landslides distinct from the environment induced by rainfall or earthquake, using the image classification method and semantic segmentation method of deep learning. However, there is a lack of research on the automatic recognition of old loess landslides, which are difficult to distinguish from the environment. Therefore, this study uses the object detection method of deep learning to identify old loess landslides with Google Earth images. At first, a database of loess historical landslide samples was established for deep learning based on Google Earth images. A total of 6111 landslides were interpreted in three landslide areas in Gansu Province, China. Second, three object detection algorithms including the one-stage algorithm RetinaNet and YOLO v3 and the two-stage algorithm Mask R-CNN, were chosen for automatic landslide identification. Mask R-CNN achieved the greatest accuracy, with an AP of 18.9% and F1-score of 55.31%. Among the three landslide areas, the order of identification accuracy from high to low was Site 1, Site 2, and Site 3, with the F1-scores of 62.05%, 61.04% and 50.88%, respectively, which were positively related to their recognition difficulty. The research results proved that the object detection method can be employed for the automatic identification of loess landslides based on Google Earth images.

Zhouqu County in Gansu Province, Northwest China, is typically highly prone to landslides. On July 12, 2018, a landslide blocked the Bailong River near Zhouqu County, posing a serious threat to the life and property of local residents and the safety of infrastructure. Small baseline subset interferometry synthetic aperture radar technology (SBAS-InSAR) was adopted to identify the potential active landslides in the surrounding area of Zhouqu County, using ascending and descending orbit Sentinel-1 satellite images taken from October 2017 to December 2018. The surface deformation areas detected by SBAS-InSAR were verified by optical remote sensing image interpretation and field investigation, and a total of 23 active landslides were identified finally. The deformation characteristics of four typical landslides are analysed in detail using deformation velocity and rainfall data. It is found that the deformation velocity of landslides in this area is mainly affected by rainfall and there is a lag effect. The results can provide a reference for the prevention and control of landslide risk in Zhouqu County.