Search Results (11)

The Loess Plateau is highly susceptible to landslides due to its fragile geological structure and frequent human activities, particularly old landslides with historical structural damage. The features of these landslides in remote sensing images become blurred over time, leading to huge challenges in detection. Considering that old landslides exhibit obvious shape characteristics, we propose ResU-SPMNet, a deep learning model that integrates shape characteristics into the baseline ResU-Net. The proposed model consists of three components: ResU-Net, shape prior module (SPM), and the atrous spatial pyramid pooling (ASPP) module, which jointly enhance segmentation performance from the perspectives of shape constraints and multi-scale feature representation. To validate the effectiveness of the proposed approach, old landslides in representative regions of the Loess Plateau were selected as the study targets. Results show that the proposed model outperforms ResU-Net, SegNet, MultiResUnet, and DeepLabv3+ in old landslide segmentation, achieving an F1-score of 0.6669 and an MCC of 0.6167. Moreover, generalization tests conducted in independent regions indicate that the model exhibits strong robustness across different seasons. The best performance is achieved in summer, whereas performance declines in winter due to adverse factors such as reduced illumination and snow or ice cover. Full article

Old landslide reactivation poses a significant risk to infrastructure and settlements in mountainous regions. Its identification and accurate localization are crucial for mitigating reactivation hazards, yet are hindered by blurred morphological signatures and vegetation cover. This study develops a cross-regional workflow for the detection and GIS-based localization of old landslides using one-meter-resolution optical imagery and an enhanced YOLOv5 model. The workflow strictly separates training and detecting areas (Wanzhou for training, Zigui for detecting) to simulate realistic, unsurveyed scenarios. A Python script converts model outputs into shapefiles with precise geographic coordinates. The results show an F1 score of 0.96 in the training area and 0.62 (mAP@0.5 = 0.58, Precision = 0.56, Recall = 0.67) in the detecting area. The analysis identifies causes of cross-regional performance degradation, including geomorphic confusion and potential detection of previously unmapped old landslides. These results demonstrate the feasibility of cross-regional landslide detection and highlight the potential of deep learning–GIS integration for practical hazard management. Full article

Urban expansion in coastal areas involves infrastructure development, industrial growth, and mining activities. These coastal environments face various environmental and geological hazards that require geo-engineers to devise solutions. An integrated geophysical approach aims to address such complex challenges as sea level rise, sea water intrusion, shoreline erosion, landslides and previous anthropogenic activity in coastal settings. In this study, the proposed methodology involves the systematic application of geophysical methods (FDEM, 3D GPR, 3D ERT, seismic), starting with a broad-scale survey and then proceeding to a localized exploration, in order to identify lithostratigraphy, bedrock depth, sea water intrusion and detect anthropogenic buried features. The critical aspect is to leverage the unique strengths and limitations of each method within the coastal environment, so as to derive valuable insights for survey design (extension and orientation of measurements) and data interpretation. The coastal zone of Throrikos valley, Attica, Greece, serves as the test site of our geophysical investigation methodology. The planning of the geophysical survey included three phases: The application of frequency-domain electromagnetic (FDEM) and 3D ground penetrating radar (GPR) methods followed by a 3D electrical resistivity tomography (ERT) survey and finally, using the seismic refraction tomography (SRT) and multichannel analysis of surface waves (MASW). The FDEM method confirmed the geomorphological study findings by revealing the paleo-coastline, superficial layers of coarse material deposits and sea water preferential flow due to the presence of anthropogenic buried features. Subsequently, the 3D GPR survey was able to offer greater detail in detecting the remains of an old marble pier inland and top layer relief of coarse material deposits. The 3D ERT measurements, deployed in a U-shaped grid, successfully identified the anthropogenic feature, mapped sea water intrusion, and revealed possible impermeable formation connected to the bedrock. ERT results cannot clearly discriminate between limestone or deposits, as sea water intrusion lowers resistivity values in both formations. Finally, SRT, in combination with MASW, clearly resolves this dilemma identifying the lithostratigraphy and bedrock top relief. The findings provide critical input for engineering decisions related to foundation planning, construction feasibility, and preservation of coastal infrastructure. The methodology supports risk-informed design and sustainable development in areas with both natural and cultural heritage sensitivity. The applied approach aims to provide a complete information package to the modern engineer when faced with specific challenges in coastal settings. Full article

Landslides are a kind of geological hazard with great destructive potential. When a landslide event occurs, a reliable landslide segmentation method is important for assessing the extent of the disaster and preventing secondary disasters. Although deep learning methods have been applied to improve the efficiency of landslide segmentation, there are still some problems that need to be solved, such as the poor segmentation due to the similarity between old landslide areas and the background features and missed detections of small-scale landslides. To tackle these challenges, a proposed high-resolution semantic segmentation algorithm for landslide scenes enhances the accuracy of landslide segmentation and addresses the challenge of missed detections in small-scale landslides. The network is based on the high-resolution network (HR-Net), which effectively integrates the efficient channel attention mechanism (efficient channel attention, ECA) into the network to enhance the representation quality of the feature maps. Moreover, the primary backbone of the high-resolution network is further enhanced to extract more profound semantic information. To improve the network’s ability to perceive small-scale landslides, atrous spatial pyramid pooling (ASPP) with ECA modules is introduced. Furthermore, to address the issues arising from inadequate training and reduced accuracy due to the unequal distribution of positive and negative samples, the network employs a combined loss function. This combined loss function effectively supervises the training of the network. Finally, the paper enhances the Loess Plateau landslide dataset using a fractional-order-based image enhancement approach and conducts experimental comparisons on this enriched dataset to evaluate the enhanced network’s performance. The experimental findings show that the proposed methodology achieves higher accuracy in segmentation performance compared to other networks. Full article

Old landslides in the Loess Plateau, Northwest China usually occurred over a relatively long period, and their sizes are usually smaller compared to old landslides in the alpine valley areas of Sichuan, Yunnan, and Southeast Tibet. These landslide areas may have been changed either partially or greatly, and they are usually covered with vegetation and similar to their surrounding environment. Therefore, it is a great challenge to detect them using high-resolution remote sensing images with only orthophoto view. This paper proposes the optimal-view and multi-view strategic hybrid deep learning (OMV-HDL) method for old loess landslide detection. First, the optimal-view dataset in the Yan’an area (YA-OP) was established to solve the problem of insufficient optical features in orthophoto images. Second, in order to make the process of interpretation more labor-saving, the optimal-view and multi-view (OMV) strategy was proposed. Third, hybrid deep learning with weighted boxes fusion (HDL-WBF) was proposed to detect old loess landslides effectively. The experimental results with the constructed optimal-view dataset and multi-view data show that the proposed method has excellent performance among the compared methods—the F1 score and AP (mean) of the proposed method were improved by about 30% compared with the single detection model using traditional orthophoto-view data—and that it has good detection performance on multi-view data with the recall of 81.4%. Full article

A considerable number of coal mines employed room and pillar mining in the last century in northern China, where the goaf remained stable for a period of time; however, with the increased exposure of coal pillars, their collapse may gradually increase. The stability assessment of these old rooms and pillar goafs is challenging due to their concealment, irregular mining patterns, and the long passage of time. The methodology developed in this study, based on “space-sky-earth” remote sensing such as InSAR to trace historical deformation, the UAV observation of current surface damage, and comparison of mining spaces, can rapidly detect on a large scale the collapse of old goafs and the trend of damage. This study is conducted with an example of a coal mine in Yulin, Northern China, where obtained quantitative surface deformation values were integrated with qualitative surface damage interpretation results, followed by a yearly analysis of the overlying rock movement in accordance with the underground coal mining process. The results show that from 2007 to 2021, corresponding surface deformation and damage occurred following mining progress. However, the room and pillar goaf areas had not undergone any surface deformation, nor had there been incidents of landslides or ground fissures; therefore, it was speculated that no roof collapse had occurred in this region. The surface deformation and damage associated with underground coal mining are complex and influenced by the coal seam occurrence, mining methods, strata lithology, terrain slope, temporal evolution, and anthropogenic modifications. These phenomena are representative of the coal mining area, and this methodology can provide a reference for similar endeavors. Full article

The reactivation of old landslides can be triggered by heavy destructive earthquakes, heavy rainfall, and ongoing human activities, thereby resulting in the occurrence of secondary landslides. However, most existing models are designed for detecting nascent landslides and there are few algorithms for old landslide detection. In this paper, we introduce a novel landslide detection model known as YOLOv8-CW, built upon the YOLOv8 (You Only Look Once) architecture, to tackle the formidable challenge of identifying old landslides. We replace the Complete-IoU loss function in the original model with the Wise-IoU loss function to mitigate the impact of low-quality samples on model training and improve detection recall rate. We integrate a CBAM (Convolutional Block Attention Module) attention mechanism into our model to enhance detection accuracy. By focusing on the southwest river basin of the Sichuan–Tibet area, we collect 558 optical remote sensing images of old landslides in three channels from Google Earth and establish a dataset specifically for old landslide detection. Compared to the original model, our proposed YOLOv8-CW model achieves an increase in detection accuracy of 10.9%, recall rate of 6%, and F1 score from 0.66 to 0.74, respectively. These results demonstrate that our improved model exhibits excellent performance in detecting old landslides within the Sichuan–Tibet area. Full article

Landslides pose a greater potential risk to the Sichuan-Tibet Transportation Project, and extensive landslide inventory and mapping are essential to prevent and control geological hazards along the Sichuan-Tibet Transportation Corridor (STTC). Recently proposed landslide detection methods mainly focused on new landslides with high vegetation. In addition, there are still challenges in automatic detection of old landslides using optical images. In this paper, two methods, namely mask region-based convolutional neural networks (Mask R-CNN) and transfer learning Mask R-CNN (TL-Mask R-CNN), are presented for detecting and segmenting new and old landslides, respectively. An optical remote sensing dataset for landslide recognition along the Sichuan-Tibet Transportation Corridor (LRSTTC) is constructed as an evaluation benchmark. Our experimental results show that the recall rate and F1-score of the proposed method for new landslide detection can reach 78.47% and 79.80%, respectively. Transfer learning is adopted to detect old landslides, and our experimental results show that evaluation indices can be further improved by about 10%. Furthermore, TL-Mask R-CNN has been applied to identify ice avalanches based on the characteristics of landslides. It appears that our proposed methods can detect and segment landslides effectively along the STTC with the constructed LRSTTC dataset, which is essential for studying and preventing landslide hazards in mountainous areas. Full article

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. Full article

Some landslides around the world that have low-angle failure planes show exceptionally poor mechanical properties. In some cases, an extraordinarily pure clay layer has been detected on the rupture surface. In this work, a complex landslide, the so-called Diezma landslide, is investigated in a low- to moderate-relief region of Southeast Spain. In this landslide, movement was concentrated on several surfaces that developed on a centimeter-thick layer of smectite (montmorillonite-beidellite) clay-rich level. Since these clayey levels have a very low permeability, high plasticity, and low friction angle, they control the stability of the entire slide mass. Specifically, the triggering factor of this landslide seems to be linked to the infiltration of water from a karstic aquifer located in the head area. The circulation of water through old failure planes could have promoted the active hydrolysis of marly soils to produce new smectite clay minerals. Here, by using geophysical, mineralogical, and geochemical modelling methods, we reveal that the formation and dissolution of carbonates, sulfates, and clay minerals in the Diezma landslide could explain the elevated concentrations of highly plastic secondary clays in its slip surface. This study may help in the understanding of landslides that show secondary clay layers coinciding to their low-angle failure planes. Full article

“La Sorbella” is a deep-seated existing landslide in a Miocene clayey formation located in central Italy. Given the interaction with a national road, this landslide has been monitored for a long time with inclinometers and hydraulic piezometers. Recently, the monitoring system was implemented by adding pressure transducers in the Casagrande cells and by equipping the old inclinometers with in-place probes, to allow a remote reading of the instruments and data recording. This system allowed to identify that the very small average rate of movement observed over one year (1.0–1.5 cm/year) is the sum of small single sliding processes, strictly linked to the sequence of rainfall events. Moreover, data recorded by in-place inclinometer probes detected the response of the landslide to the seismic sequence of 2016 occurring in central Italy. Such in situ measurements during earthquakes, indeed rarely available in the scientific literature, allowed an assessment of the critical acceleration of the sliding mass by means of a back-analysis. The possibility to distinguish the difference between seismic and rainfall induced displacements of the slope underlines the potential of continuous monitoring in the diagnosis of landslide mechanisms. Full article