Search

Landslides are the most serious geological disaster in our country, causing economic losses. Because they go undetected, a large number of landslides that have caused disasters are not in the catalogue. At present, Interferometric Synthetic Aperture Radar (InSAR) has been widely used in the identification of landslides. However, it is time-consuming, inefficient, etc., to survey landslides throughout our large country. In the context of massive SAR data, this problem is more obvious. Therefore, based on the current technique of using differential interferogram phase gradient stacking to avoid phase unwrapping errors, a landslide phase gradient dataset has been constructed. To validate the dataset's effectiveness and applicability, deep learning methods were introduced, applying the dataset to four networks: U-Net, Attention-Unet, Bisenet v2, and Deeplab v3. The results indicate that the phase gradient dataset performs well across different models, with the Attention-Unet network demonstrating the best performance. Specifically, the precision, recall, and accuracy on the test dataset were 0.8771, 0.8712, and 0.9834, respectively, and the accuracy on the validation dataset was 0.8523. Finally, in this paper, the model is applied to landslide identification in Gansu Province, China, during 2022-2023, and a total of 1882 landslides are found. These landslides are mainly concentrated in the south of Gansu Province, where the terrain is relatively undulating. The results show that this method can quickly and accurately realize landslide automatic identification in a wide area and provide technical support for large-scale landslide disaster surveys. [ABSTRACT FROM AUTHOR]

The Meijiayan landslide in Pengshui County within Chongqing City is a medium-scale soil landslide triggered by the excavation of roadbeds. To delve into the influencing factors and assess the stability of this landslide, it is crucial to meticulously map the subterranean geological framework of the area. Such an analysis lays the groundwork for evaluating and mitigating the risks of future landslide instabilities. In this context, the semi-airborne transient electromagnetic method (SATEM), which is complemented by a receiving system mounted on an aerial platform, stands out as an innovative geophysical exploration technique. This method is adept at conducting swift measurements across complex terrains, making it particularly valuable for areas prone to such geological events. This paper presents the utilization of a cutting-edge loop source SATEM system, which was operationalized via a rotor-based unmanned aerial vehicle (UAV). The system was employed to conduct shallow geological structure detection experiments on the Meijiayan landslide. The SATEM detection outcomes have unveiled fluctuations in the electrical distribution across the upper strata, which are indicative of the subsurface geological boundaries, faults, and areas potentially rich in water within the landslide region. These discoveries affirm the viability of utilizing loop source SATEM for the identification of shallow geological structures in regions susceptible to landslides. The findings indicate that while the landslide is currently in a stable condition, it poses a significant risk of movement, especially during the rainy season, with the potential for landslides to be exacerbated by extreme or sustained rainfall events. [ABSTRACT FROM AUTHOR]

This paper systematically reviews remote sensing technology and learning algorithms in exploring landslides. The work is categorized into four key components: (1) literature search characteristics, (2) geographical distribution and research publication trends, (3) progress of remote sensing and learning algorithms, and (4) application of remote sensing techniques and learning models for landslide susceptibility mapping, detections, prediction, inventory and deformation monitoring, assessment, and extraction and management. The literature selections were based on keyword searches using title/abstract and keywords from Web of Science and Scopus. A total of 186 research articles published between 2011 and 2024 were critically reviewed to provide answers to research questions related to the recent advances in the use of remote sensing technologies combined with artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms. The review revealed that these methods have high efficiency in landslide detection, prediction, monitoring, and hazard mapping. A few current issues were also identified and discussed. [ABSTRACT FROM AUTHOR]

The lack of high-resolution training sets for intelligent landslide recognition using high-resolution remote sensing images is a major challenge. To address this issue, this paper proposes a method for reconstructing low-resolution landslide remote sensing images based on a Super-Resolution Generative Adversarial Network (SRGAN) to fully utilize low-resolution images in the process of constructing high-resolution landslide training sets. First, this paper introduces a novel Enhanced Depth Residual Block called EDCA, which delivers stable performance compared to other models while only slightly increasing model parameters. Secondly, it incorporates coordinated attention and redesigns the feature extraction module of the network, thus boosting the learning ability of image features and the expression of high-frequency information. Finally, a residual stacking-based landslide remote sensing image reconstruction strategy was proposed using EDCA residual blocks. This strategy employs residual learning to enhance the reconstruction performance of landslide images and introduces LPIPS for evaluating the test images. The experiment was conducted using landslide data collected by drones in the field. The results show that compared with traditional interpolation algorithms and classic deep learning reconstruction algorithms, this approach performs better in terms of SSIM, PSNR, and LPIPS. Moreover, the network can effectively handle complex features in landslide scenes, which is beneficial for subsequent target recognition and disaster monitoring. [ABSTRACT FROM AUTHOR]

In this paper, Feature Engineering (FE) was applied to Landslide Susceptibility Mapping (LSM), while the most suitable conditioning feature dataset and analysis method were tested and analyzed. Tianshui city was taken as the study area, three types of geohazard (collapse, landslide, and unstable slopes) were used, while a total of twenty-three conditioning features were generated; two dimensionless methods (normalization and standardization) were tested afterward. Four Random-Forest-based (RF-based) feature selection methods using different indicators (Gini Impurity, GI; Out of Bag Accuracy, OOBA) were proposed and tested separately. The LSMs of four models were carried out under the guidance results of FE, namely Classification and Regression Tree (CART), Random Forest (RF), Logistic Regression (LR), and Support Vector Machine for Classification (SVC). For feature enhancement, standardization had significant advantages over normalization. All RF-based methods were proven effective, lifting the AUC by 0.01~0.02. The RF model achieved the highest LSM accuracies, respectively, 0.949 (landslide), 0.957, and 0.949 (unstable slopes), improved by 0.008 (landslide), 0.005 (collapse), and 0.013 (unstable slopes). This proved that the FE helped to improve LSM and can help to decide the dominant conditioning factors for regional geohazards. [ABSTRACT FROM AUTHOR]

The landslide monitoring method that uses the Sentinel 1A Interferogram Synthetic Aperture Radar (InSAR) through the Stanford Method for Persistent Scatterers (StaMPS) method is a complimentary but complex procedure without exact guidelines. Hence, this paper delivered a parametric test by examining the optimal settings of the Sentinel 1A Persistent Scatterer (PS)- and Small Baseline Subset (SBAS)-InSAR using the StaMPS compared to the Global Navigation Satellite Systems (GNSS) in landslide cases. This study first revealed parameters with the suggested values, such as amplitude dispersion used to describe amplitude stability, ranging from 0.47 to 0.48 for PS and equal to or more than 0.6 for SBAS in WuWanZai, Ali Mt. The study further examined the suggested values for other factors, including the following: unwrap grid size to re-estimate the size of the grid; unwrap gold n win as the Goldstein filtering window to reduce the noise; and unwrap time win as the smoothing window (in days) for estimating phase noise distributions between neighboring pixels. Furthermore, the study substantiated the recommended settings in the Woda and Shadong landslide cases with the GNSS, inferring that the SBAS has adequate feasibility in practical landslide monitoring. [ABSTRACT FROM AUTHOR]

Landslide prediction is one of the complicated topics recognized by the global scientific community. The research on landslide susceptibility prediction is vitally important to mitigate and prevent landslide disasters. The instability and complexity of the landslide system can cause uncertainty in the prediction process and results. Although there are many types of models for landslide susceptibility prediction, they still do not have a unified theoretical basis or accuracy test standard. In the past, models were mainly subjectively selected and determined by researchers, but the selection of models based on subjective experience often led to more significant uncertainty in the prediction process and results. To improve the universality of the model and the reliability of the prediction accuracy, it is urgent to systematically summarize and analyze the performance of different models to reduce the impact of uncertain factors on the prediction results. For this purpose, this paper made extensive use of document analysis and data mining tools for the bibliometric and knowledge mapping analysis of 600 documents collected by two data platforms, Web of Science and Scopus, in the past 40 years. This study focused on the uncertainty analysis of four key research subfields (namely disaster-causing factors, prediction units, model space data sets, and prediction models), systematically summarized the difficulties and hotspots in the development of various landslide prediction models, discussed the main problems encountered in these four subfields, and put forward some suggestions to provide references for further improving the prediction accuracy of landslide disaster susceptibility. [ABSTRACT FROM AUTHOR]

Wide area landslide detection is a major international research hotspot in the field of geological hazards, and the integration of multi-temporal optical satellite images and spaceborne interferometric synthetic aperture radar (InSAR) appears to be an effective way to realize this. In this paper, a technical framework is presented for wide area landslide detection: (i) multi-temporal satellite optical images are used to detect landslides with distinguishable geomorphological features; (ii) Generic Atmospheric Correction Online Service (GACOS) assisted InSAR stacking is employed to generate annual surface displacement rate maps in radar line of sight using satellite SAR images from both ascending and descending tracks, which are in turn utilized to automatically detect active landslides from ground motion using hotspot analysis, and (iii) the distribution characteristics of the detected landslides are investigated by examining their relationships with topographic and hydrological factors. Three expressways in Sichuan Province, China—namely the Yakang (Ya'an-Kangding), Yaxi (Ya'an-Xichang), and Lushi (Luding-Shimian) expressways—and their surrounding regions (a total area of approximately 20,000 square kilometers) were chosen as the study area. A total of 413 landslides were detected, among which 320 were detected using multi-temporal satellite optical images, and 109 were detected using GACOS-assisted InSAR stacking. It should be noted that only 16 landslides were detected by both approaches; these landslides all exhibited not only obvious geomorphological features but also ground motion. A statistical analysis of the topographic and hydrological factors shows that of the detected landslides: 81% are distributed at elevations of 1000–2500 m, over 60% lie within the elevation range of 100~400 m, and 90% present with medium and steep slopes (20°~45°), and 80% are located within areas seeing an annual rainfall of 950~1050 mm. Nine landslides were found to pose potential safety hazards to the expressways. The research findings in this paper have directly benefitted the Sichuan expressways; equally important, it is believed that the technical framework presented in this paper will provide guidance for hazard mitigation and the prevention of transportation hazards in the future. [ABSTRACT FROM AUTHOR]

This paper presents a multi-temporal comparison of high-resolution 3D digital models from two urban areas susceptible to landslides in three time periods. The study areas belong to the São Paulo landslide risk mapping database and are named "CEU Paz" (CP) and "Parque Santa Madalena I" (PSM). For each area, a lidar digital surface model (DSM) (2017) and two structure-from-motion multi-view stereo DSMs (2019 and 2022) built from drone imagery were combined using raster algebra to generate three digital surface models of differences (DoDs). The DoDs were able to highlight changes in vegetation cover and buildings, which are important characteristics for evaluating geological risks in an urban context. Still, they were unable to highlight changes in the ground surface. The results demonstrate that the method greatly supports monitoring, allowing for greater detail and ease of detecting large-scale changes. Even with promising results, this technique should be understood as one more tool for mapping risk areas without replacing fieldwork. [ABSTRACT FROM AUTHOR]

The current limited approaches to calculating hillslope erosion rate hamper the study of the relationships among the rates of hillslope erosion, river incision, and tectonic uplift and hence the discussion of steady-state landscape evolution. In this paper, we use remote sensing and geochronological methods to calculate the upper and lower bounding hillslope erosion rates in the Qilian Shan range, Tibet. Our analysis focuses on five convex landslide sediment units derived from the weathered hillslopes at Qingyang Mountain on the tectonically active northeastern Tibetan Plateau. These sediment units range in thickness from 5.5 to 12.8 m and in volume from 119 × 103 to 260 × 103 m3. Based on field observations, measurements extracted from high-resolution DEMs, and optical stimulated luminescence (OSL) ages on fluvial terraces, we obtain lower and upper bounding rates of 0.13 ± 0.03 and 0.21 ± 0.04 mm/yr, respectively. Finally, we calculate incision rates, ranging from 0.21 ± 0.02 to 0.39 ± 0.01 mm/yr, from heights of a dated fluvial terrace above the present river and the time of abandonment of the associated bedrock strath estimated from OSL ages. The rates of hillslope erosion and river incision at Qingyang Mountain and the tectonic uplift of the Qilian Mountains are estimated to be within a factor of two over the past 117 ka, suggesting that a state of dynamic equilibrium has likely existed on this timescale. [ABSTRACT FROM AUTHOR]

This paper presents a new hybrid ensemble modeling method called BBO-DE-STreeEns for land-slide susceptibility mapping in Than Uyen district, Vietnam. The method uses subbagging and random subspacing to generate subdatasets for constituent classifiers of the ensemble model, and a split-point and attribute reduced classifier (SPAARC) decision tree algorithm to build each classifier. To optimize hyperparameters of the ensemble model, a hybridization of biogeography-based optimization (BBO) and differential evolution (DE) algorithms is adopted. The land-slide database for the study area includes 114 landslide locations, 114 non-landslide locations, and ten influencing factors: elevation, slope, curvature, aspect, relief amplitude, soil type, geology, distance to faults, distance to roads, and distance to rivers. The database was used to build and verify the BBO-DE-StreeEns model, and standard statistical metrics, namely, positive predictive value (PPV), negative predictive value (NPV), sensitivity (Sen), specificity (Spe), accuracy (Acc), Fscore, Cohen's Kappa, and the area under the ROC curve (AUC), were calculated to evaluate prediction power. Logistic regression, multi-layer perceptron neural network, support vector machine, and SPAARC were used as benchmark models. The results show that the proposed model outperforms the benchmarks with a high prediction power (PPV = 90.3%, NPV = 83.8%, Sen = 82.4%, Spe = 91.2%, Acc = 86.8%, Fscore = 0.862, Kappa = 0.735, and AUC = 0.940). Therefore, the BBO-DE-StreeEns method is a promising tool for landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

Bivariate data-driven methods have been widely used in landslide susceptibility analysis. However, the names, principles, and correlations of bivariate methods are still confused. In this paper, the names, principles, and correlations of bivariate methods are first clarified based on a comprehensive and in-depth survey. A total of eleven prevalent bivariate methods are identified, nominated, and elaborated in a general framework, constituting a well-structured bivariate method family. We show that all prevalent bivariate methods depend on empirical conditional probabilities of landslide occurrence to calculate landslide susceptibilities, either exclusively or inclusively. It is clarified that those eight "conditional-probability-based" bivariate methods, which exclusively depend on empirical conditional probabilities, are particularly strongly correlated in principle, and therefore are expected to have a very close or even the same performance. It is also suggested that conditional-probability-based bivariate methods apply to a "classification-free" modification, in which factor classifications are avoided and the result is dominated by a single parameter, "bin width". Then, a general optimization framework for conditional-probability-based bivariate methods, based on the classification-free modification and obtaining optimum results by optimizing the dominant parameter bin width, is proposed. The open software Automatic Landslide Susceptibility Analysis (ALSA) is updated to implement the eight conditional-probability-based bivariate methods and the general optimization framework. Finally, a case study is presented, which confirms the theoretical expectation that different conditional-probability-based bivariate methods have a very close or even the same performance, and shows that optimal bivariate methods perform better than conventional bivariate methods regarding both the prediction rate and the ability to reveal the quasi-continuous varying pattern of sensibilities to landslides for individual predisposing factors. The principles and open software presented in this study provide both theoretical and practical foundations for applications and explorations of bivariate methods in landslide susceptibility analysis. [ABSTRACT FROM AUTHOR]

Landslides, as one of the main problems in mountainous areas, are a challenging issue for modern geophysics. The triggers that cause these phenomena are diverse (including geological, geomorphological, and hydrological conditions, climatic factors, and earthquakes) and can occur in conjunction with each other. Human activity is also relevant, undoubtedly contributing to the intensification of landslide phenomena. One of these is the production of artificial snow on ski slopes. This paper presents a multimethod approach for imaging the landslide structure in Cisiec, in southwestern Poland, where such a situation occurs. In the presented work, the integration of remote sensing with multi-method geophysical imaging was used to visualize landslide zones, and to estimate ground motion. To verify the uncertainty of the obtained data, the combination of electrical resistivity tomography (ERT), multi-channel analysis of surface waves (MASW), and seismic refraction method (SRT) was supported by synthetic modeling. Using geophysical data with accurate GPS-based topography and a terrestrial laser scanning-based digital terrain model (DTM), it was possible to model the spatial variability and surface area of the landslide more precisely, as well as to estimate the velocity field in the nearest surface more accurately. The final result shows displacement up to 1 m on the ground surface visible on the DTM models, while the geophysical methods confirm the change in internal structure. The proposed methodology is fast, cost-effective, and can be used to image the structure of landslides, where the shallowest parts are usually complex and thus difficult to observe seismically. [ABSTRACT FROM AUTHOR]

Landslide is a devastating natural disaster, causing loss of life and property. It is likely to occur more frequently due to increasing urbanization, deforestation, and climate change. Landslide susceptibility mapping is vital to safeguard life and property. This article surveys machine learning (ML) models used for landslide susceptibility mapping to understand the current trend by analyzing published articles based on the ML models, landslide causative factors (LCFs), study location, datasets, evaluation methods, and model performance. Existing literature considered in this comprehensive survey is systematically selected using the ROSES protocol. The trend indicates a growing interest in the field. The choice of LCFs depends on data availability and case study location; China is the most studied location, and area under the receiver operating characteristic curve (AUC) is considered the best evaluation metric. Many ML models have achieved an AUC value > 0.90, indicating high reliability of the susceptibility map generated. This paper also discusses the recently developed hybrid, ensemble, and deep learning (DL) models in landslide susceptibility mapping. Generally, hybrid, ensemble, and DL models outperform conventional ML models. Based on the survey, a few recommendations and future works which may help the new researchers in the field are also presented. [ABSTRACT FROM AUTHOR]

The southwest mountainous area of China is one of the areas with the most landslides in the world. In this paper, we used Ya'an City and Garzê Tibetan Autonomous Prefecture in Sichuan Province as the research areas to explore the identification application effects of large-area potential landslides using synthetic aperture radar (SAR) data with different wavelength types (Sentinel-1, ALOS-2), different processing methods (SBAS-InSAR, Stacking-InSAR), and different geological environmental conditions. The results show the following: (1) The effect of identifying landslides with different slope directions is largely affected by the satellite orbit direction; when we identify landslide hazards across a large area, the joint monitoring mode of ascending and descending orbit data is required. (2) The period of monitoring affects the identification effect of potential landslides when landslide identification is carried out in southwestern China; the InSAR monitoring period is recommended to be more than 2 years. (3) In different geological environmental regions, SBAS technology and Stacking technology have their own advantages; Stacking technology identifies more potential landslides, and SBAS technology identifies potential landslides with higher accuracy; (4) the degree of vegetation coverage has a great impact on the landslide identification effect of different SAR data sources. In low-density vegetation coverage areas, the landslide identification result using Sentinel-1 data seems to be better than the result using ALOS-2 data. In high-density vegetation coverage areas, the landslide identification result using ALOS-2 data is better than that using Sentinel-1 data. [ABSTRACT FROM AUTHOR]

This paper presents an analysis of the integration between interferometric and intensity-offset tracking-based SAR remote sensing for landslide hazard mitigation in the Italian Alps. Despite the advantages of Synthetic Aperture Radar Interferometry (InSAR) methods for quantifying landslide deformation, some limitations remain. The temporal decorrelation, the 1-D Line Of Sight (LOS) observation restriction, the high velocity rate and the multi-directional movement properties make it difficult to monitor accurately complex landslides in areas covered by vegetation. Therefore, complementary and integrated approaches, such as offset tracking-based techniques, are needed to overcome these InSAR limitations for monitoring ground surface deformations. As sub-pixel offset tracking is highly sensitive to data spatial resolution, the latest generations of SAR sensors, such as TerraSAR-X and COSMO-SkyMed, open interesting perspective for a more accurate hazard assessment. In this paper, we consider high-resolution X-band data acquired by the COSMO-SkyMed (CSK) constellation for Permanent Scatterers Interferometry (PSI), Multi-Aperture Interferometry (MAI) and offset tracking processing. We analyze the offset tracking techniques considering area and feature-based matching algorithms to evaluate their applicability to CSK data by improving sub-pixel offset estimations. To this end, PSI and MAI are used for extracting LOS and azimuthal displacement components. Then, four well-known area-based and five feature-based matching algorithms (taken from computer vision) are applied to 16 X-band corner reflectors. Results show that offset estimation accuracy can be considerably improved up to less than 3% of the pixel size using the combination of the different feature-based detectors and descriptors. A sensitivity analysis of these techniques applied to CSK data to monitor complex landslides in the Italian Alps provides indications on advantages and disadvantages of each of them. [ABSTRACT FROM AUTHOR]

With the increase in climate-change-related hazardous events alongside population concentration in urban centres, it is important to provide resilient cities with tools for understanding and eventually preparing for such events. Machine learning (ML) and deep learning (DL) techniques have increasingly been employed to model susceptibility of hazardous events. This study consists of a systematic review of the ML/DL techniques applied to model the susceptibility of air pollution, urban heat islands, floods, and landslides, with the aim of providing a comprehensive source of reference both for techniques and modelling approaches. A total of 1454 articles published between 2020 and 2023 were systematically selected from the Scopus and Web of Science search engines based on search queries and selection criteria. ML/DL techniques were extracted from the selected articles and categorised using ad hoc classification. Consequently, a general approach for modelling the susceptibility of hazardous events was consolidated, covering the data preprocessing, feature selection, modelling, model interpretation, and susceptibility map validation, along with examples of related global/continental data. The most frequently employed techniques across various hazards include random forest, artificial neural networks, and support vector machines. This review also provides, per hazard, the definition, data requirements, and insights into the ML/DL techniques used, including examples of both state-of-the-art and novel modelling approaches. [ABSTRACT FROM AUTHOR]

The lack of high-resolution training sets for intelligent landslide recognition using high-resolution remote sensing images is a major challenge. To address this issue, this paper proposes a method for reconstructing low-resolution landslide remote sensing images based on a Super-Resolution Generative Adversarial Network (SRGAN) to fully utilize low-resolution images in the process of constructing high-resolution landslide training sets. First, this paper introduces a novel Enhanced Depth Residual Block called EDCA, which delivers stable performance compared to other models while only slightly increasing model parameters. Secondly, it incorporates coordinated attention and redesigns the feature extraction module of the network, thus boosting the learning ability of image features and the expression of high-frequency information. Finally, a residual stacking-based landslide remote sensing image reconstruction strategy was proposed using EDCA residual blocks. This strategy employs residual learning to enhance the reconstruction performance of landslide images and introduces LPIPS for evaluating the test images. The experiment was conducted using landslide data collected by drones in the field. The results show that compared with traditional interpolation algorithms and classic deep learning reconstruction algorithms, this approach performs better in terms of SSIM, PSNR, and LPIPS. Moreover, the network can effectively handle complex features in landslide scenes, which is beneficial for subsequent target recognition and disaster monitoring.

Southeast Asia (SEA) is a region affected by landslide and wildfire; however, few studies on susceptibility modeling for the two hazards together have been conducted for this region, and the intersection and the uncertainty of the two hazards are rarely assessed. Thus, the intersection of landslide and wildfire susceptibility and the spatial uncertainty of the susceptibility maps were studied in this paper. Reliable landslide and wildfire susceptibility maps are necessary for disaster management and land use planning. This work used three advanced ensemble machine learning algorithms: RF (Random Forest), GBDT (Gradient Boosting Decision Tree) and AdaBoost (Adaptive Boosting) to assess the landslide and wildfire susceptibility for SEA. A geo-database was established with 2759 landslide locations, 1633 wildfire locations and 18 predictor variables in total. The performances of the models were assessed using the overall classification accuracy (ACC), Precision, the area under the ROC (receiver operating curve) (AUC) and confusion matrix values. The results showed RF performs superior in both landslide (ACC = 0.81, Precision = 0.78 and AUC= 0.89) and wildfire (ACC= 0.83, Precision = 0.83 and AUC = 0.91) susceptibility modeling, followed by GBDT and AdaBoost. The overall superiority of RF over other models indicates that it is potentially an efficient model for landslide and wildfire susceptibility mapping. The landslide and wildfire susceptibility were obtained using the RF model. This paper also conducted an overlay analysis of the two hazards. The uncertainty of the susceptibility was further assessed using the coefficient of variation (CV). Additionally, the distance to roads is relatively important in both landslide and wildfire susceptibility, which is the most important in landslides and the second most important in wildfires. The result of this paper is useful for mastering the whole situation of hazard susceptibility and proves that RF is a robust model in the hazard susceptibility assessment in SEA. [ABSTRACT FROM AUTHOR]

The development of landslide hazards is spatially scattered, temporally random, and poorly characterized. Given the advantages of the large spatial scale and high sensitivity of InSAR observations, InSAR is becoming one of the main techniques for active landslide identification. The difficult problem is how to quickly extract landslide information from extensive InSAR image data. Since the instance segmentation model (Mask R-CNN) in deep learning can provide highly robust target recognition, we select the landslide-prone eastern edge of the Tibetan Plateau as a specific test area. Introducing and optimizing this model achieves high-speed and accurate recognition of InSAR observations. First, the InSAR patch landslide instance segmentation dataset (SLD) is established by developing a common object in context (COCO) annotation format conversion code based on InSAR observations. The Mask R-CNN+++ is found by adding three functions of the ResNext module to increase the fineness of the network segmentation results and enhance the noise resistance of the model, the DCB (deformable convolutional block) to improve the feature extraction ability of the network for geometric morphological changes of landslide patches, and an attention mechanism to selectively enhance usefully and suppress features less valuable to the native Mask R-CNN network. The model achieves 92.94% accuracy on the test set, and the active landslide recognition speed based on this model under ordinary computer hardware conditions is 72.3 km2/s. The overall characteristics of the results of this study show that the optimized model effectively enhances the perceptibility of image morphological changes, thereby resulting in smoother recognition boundaries and further improvement of the generalization ability of segmentation detection. This result is expected to serve to identify and monitor active landslides in complex surface conditions on a large spatial scale. Moreover, active landslides of different geometric features, motion patterns, and intensities are expected to be further segmented. [ABSTRACT FROM AUTHOR]

Seismic landslides are the most common and highly destructive earthquake-triggered geological hazards. They are large in scale and occur simultaneously in many places. Therefore, obtaining landslide information quickly after an earthquake is the key to disaster mitigation and relief. The survey results show that most of the landslide-information extraction methods involve too much manual participation, resulting in a low degree of automation and the inability to provide effective information for earthquake rescue in time. In order to solve the abovementioned problems and improve the efficiency of landslide identification, this paper proposes an automatic landslide identification method named improved U-Net model. The intelligent extraction of post-earthquake landslide information is realized through the automatic extraction of hierarchical features. The main innovations of this paper include the following: (1) On the basis of the three RGB bands, three new bands, DSM, slope, and aspect, with spatial information are added, and the number of feature parameters of the training samples is increased. (2) The U-Net model structure is rebuilt by adding residual learning units during the up-sampling and down-sampling processes, to solve the problem that the traditional U-Net model cannot fully extract the characteristics of the six-channel landslide for its shallow structure. At the end of the paper, the new method is used in Jiuzhaigou County, Sichuan Province, China. The results show that the accuracy of the new method is 91.3%, which is 13.8% higher than the traditional U-Net model. It is proved that the new method is effective and feasible for the automatic extraction of post-earthquake landslides. [ABSTRACT FROM AUTHOR]

Landslide susceptibility maps (LSMs) are valuable tools typically used by local authorities for land use management and planning activities, supporting decision-makers in urban and infrastructure planning. To address this, we proposed a refined method for landslide susceptibility assessment, which comprehensively considered both static and dynamic factors. Neural network methods were used for susceptibility analysis. Land use and land cover (LULC) change and InSAR deformation were then integrated into the traditional susceptibility zoning to obtain a refined susceptibility map with higher accuracy. Validation was conducted on the improved landslide susceptibility map using site landslide data. The results showed that the LULC were proven to be the core driving factors for landslide occurrence in the study area. The GRU model achieved the highest model performance (AUC = 0.886). The introduction of InSAR surface deformation and land use and land cover change data could rationalize the inappropriateness of traditional landslide susceptibility zoning, correcting the false positive and false negative areas in the traditional landslide susceptibility map caused by human activities. Ultimately, 12.25% of the study area was in high-susceptibility zones, with 3.10% of false positive and 0.74% of false negative areas being corrected. The proposed method enabled refined analysis of landslide susceptibility over large areas, providing technical support and disaster prevention and mitigation references for geological hazard susceptibility assessment and land management planning. [ABSTRACT FROM AUTHOR]

Vegetation recovery monitoring is critical for assessing denudation areas after landslides have occurred. A long-term and broad area investigation using remote sensing techniques is an efficient and cost-effective approach incorporating the consideration of radiometric correction and seasonality variations across multi-date satellite images. This paper investigates long-term vegetation recovery using 14 SPOT satellite images spanning from 1999 to 2011 over the landslide area of Mt. Jou-Jou in central Taiwan, which was caused by the Chi-Chi earthquake in 1999. The vegetation status was evaluated by the Normalized Difference Vegetation Index (NDVI) with radiometric correction between multi-date images based on pseudoinvariant features, and subsequently a vegetation recovery rate (VRR) model was empirically established after seasonality adjustment was performed on the multi-date NDVI images. An increasing tendency of the vegetation recovery in the landslide area of Mt. Jou-Jou appeared based on the NDVI value rising to 0.367 in March 2011 from -0.044 right after the catastrophic earthquake. The vegetation recovery rate with seasonality adjustment approached 81.5% for the total area and 81.3% for the landslide area through 12 years succession. The seasonality adjustment also enhanced the VRR model with a determination coefficient that increased from 0.883 to 0.916 for the landslide area and from 0.584 to 0.915 for the total area, highlighting the necessity of seasonality adjustment in multi-date vegetation observations using satellite images. Furthermore, the association between precipitation and NDVI was discussed, and the inverse relationship with the reoccurrence of high-intensity short-duration rainfall and yearly heavy rainfall was observed, in agreement with the on-site investigation. [ABSTRACT FROM AUTHOR]

With the development of high-resolution Synthetic Aperture Radar (SAR) systems, researchers are increasingly paying attention to the application of SAR offset tracking methods in ground deformation estimation. The traditional normalized cross correlation (NCC) tracking method is based on regular matching windows. For areas with different moving characteristics, especially the landslide boundary areas, the NCC method will produce incorrect results. This is because in landslide boundary areas, the pixels of the regular matching window include two or more types of moving characteristics: some pixels with large displacement, and others with small or no displacement. These two kinds of pixels are uncorrelated, which result in inaccurate estimations. This paper proposes a new offset tracking method with SAR images based on the adaptive matching window to improve the accuracy of landslide displacement estimation. The proposed method generates an adaptive matching window that only contains pixels with similar moving characteristics. Three SAR images acquired by the Jet Propulsion Laboratory's Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) system are selected to estimate the surface deformation of the Slumgullion landslide located in the southwestern Colorado, USA. The results show that the proposed method has higher accuracy than the traditional NCC method, especially in landslide boundary areas. Furthermore, it can obtain more detailed displacement information in landslide boundary areas. [ABSTRACT FROM AUTHOR]

Over the last 10 years, the accessibility of high spatial resolution remote sensing images has strongly increased. These images are available in ortho-rectified format which do not necessitate any further geometrical processing to be analyzed. In parallel, image correlation software has become more efficient and friendly. In this paper, image correlation methods are tested to evaluate their potential and limitations to measure the surface displacements in a complex case of a landslide located in a tropical environment. This studied landslide, called "Mare à Poule d'Eau", is located in the Salazie erosion watershed in Réunion Island (France). This landslide is monitored daily by a DGPS station which registers the south-north displacements. Two pairs of ortho-rectified SPOT-5 images at 2.5 m resolution provided by Kalideos (http://kalideos.cnes.fr) were selected. The first pair frames the period between 2002 and 2005 during which the landslide activity was low. The second pair of images (2006-2008) frames a period of time during which the landslide was more active. Fifty-nine Image Control Points (ICP) were selected on the images by the SIFT method (Scale Invariant Feature Transform) and visually controlled. The shifts of these points used as external control are estimated for the two time periods. Two image correlator softwares are used: MicMac and Cosi-Corr. The results obtained by the two correlators are similar. For the 2002-2005 period, the shift measured by correlators in the landslide is similar to the shift outside the landslide. This means that the displacement cannot be detected and estimated during periods of low activity of the landslide. The shift of the landslide for the 2006-2008 period is out of noise and reaches 8.5 m. The displacement can be estimated by applying a correction factor extracted from the ICP located in the stable areas. The potential and limits of the image correlation in such complex environments is discussed. A strategy is proposed to evaluate the quality of the results and to extract the displacement signal from the shift measurements. [ABSTRACT FROM AUTHOR]

Against the backdrop of global warming and increased rainfall, the hazards and potential risks of landslides are increasing. The rapid generation of a landslide inventory is of great significance for landslide disaster prevention and reduction. Deep learning has been widely applied in landslide identification due to its advantages in terms of its deeper model structure, high efficiency, and high accuracy. This article first provides an overview of deep learning technology and its basic principles, as well as the current status of landslide remote sensing databases. Then, classic landslide deep learning recognition models such as AlexNet, ResNet, YOLO, Mask R-CNN, U-Net, Transformer, EfficientNet, DeeplabV3+ and PSPNet were introduced, and the advantages and limitations of each model were extensively analyzed. Finally, the current constraints of deep learning in landslide identification were summarized, and the development direction of deep learning in landslide identification was analyzed. The purpose of this article is to promote the in-depth development of landslide identification research in order to provide academic references for the prevention and mitigation of landslide disasters and post-disaster rescue work. The research results indicate that deep learning methods have the characteristics of high efficiency and accuracy in automatic landslide recognition, and more attention should be paid to the development of emerging deep learning models in landslide recognition in the future. [ABSTRACT FROM AUTHOR]

This article presents a methodology for evaluating the susceptibility of landfill areas to develop landslides by analyzing Synthetic Aperture Radar (SAR) satellite products. The deformation velocity of the landfills is computed through the Persistent Scatterer Method on SAR imagery. These data, combined with a deformation model based on the shallow water equations (SWE), form the foundation for a Monte Carlo experiment that extrapolates the current state of the landfill into the future. The results of this simulation are then employed to determine the probability of a landslide occurrence. In order to validate the methodology effectiveness, a case study is conducted on a landfill in Zaldibar, Spain, revealing its effectiveness in estimating the probability of landfill landslides. This innovative approach emerges as an asset in large landfill management, acting as a proactive tool for identifying high-risk sites and preventing potential landslides, ultimately safeguarding human life and the environment. By providing insights into landslide probabilities, this study enhances decision-making processes and facilitates the development of intervention strategies in the domain of landfill risk assessment and management. [ABSTRACT FROM AUTHOR]

Mount Meager is a deeply eroded quaternary volcanic complex located in southwestern British Columbia (BC) and is known for its frequent large landslides. In 2010, the south face of Mount Meager collapsed, generating a long-runout debris avalanche that was one of the largest landslides (50 × 106 m3) in Canadian history. Over the past 14 years, the landslide deposit has been reworked by stream action, delivering large amounts of sediment to Lillooet River, just downstream. In this study, we investigate 10 years of geomorphic evolution of the landslide deposit using orthophotos and digital elevation models (DEMs) generated using Structure from Motion (SfM) photogrammetry on aerial photographs acquired during unmanned aerial vehicle (UAV) and Global Navigation Satellite System (GNSS) surveys. The SfM products were used to produce a series of precise maps that highlight the geomorphological changes along the lower Meager Creek within the runout area of the landslide. Comparison of DEMs produced from 2010, 2012, 2015, and 2019 imagery allowed us to calculate deposit volume changes related to erosion, transport, and redeposition of landslide material. We estimate that about 1.1 × 106 m3 of sediment was eroded from the landslide deposit over the period 2015–2019. About 5.2 × 105 m3 of that sediment was redeposited inside the study area. About 5.8 × 105 m3 of sediment, mainly sand, silt, and clay, were exported from the study area and are being carried by Lillooet River towards Pemberton, 40 km from Mount Meager, and farther downstream. These remobilized sediments likely reduce the Lillooet River channel capacity and thus increase flood hazards to the communities of Pemberton and Mount Currie. Our study indicates a landslide persistence in the landscape, with an estimated 47-year half-life decay, suggesting that higher flood hazard conditions related to increased sediment supply may last longer than previously estimated. This study shows the value of using SfM in tandem with historic aerial photographs, UAV photos, and high-resolution satellite imagery for determining sediment budgets in fluvial systems. [ABSTRACT FROM AUTHOR]

Wide area landslide detection is a major international research hotspot in the field of geological hazards, and the integration of multi-temporal optical satellite images and spaceborne interferometric synthetic aperture radar (InSAR) appears to be an effective way to realize this. In this paper, a technical framework is presented for wide area landslide detection: (i) multi-temporal satellite optical images are used to detect landslides with distinguishable geomorphological features; (ii) Generic Atmospheric Correction Online Service (GACOS) assisted InSAR stacking is employed to generate annual surface displacement rate maps in radar line of sight using satellite SAR images from both ascending and descending tracks, which are in turn utilized to automatically detect active landslides from ground motion using hotspot analysis, and (iii) the distribution characteristics of the detected landslides are investigated by examining their relationships with topographic and hydrological factors. Three expressways in Sichuan Province, China—namely the Yakang (Ya’an-Kangding), Yaxi (Ya’an-Xichang), and Lushi (Luding-Shimian) expressways—and their surrounding regions (a total area of approximately 20,000 square kilometers) were chosen as the study area. A total of 413 landslides were detected, among which 320 were detected using multi-temporal satellite optical images, and 109 were detected using GACOS-assisted InSAR stacking. It should be noted that only 16 landslides were detected by both approaches; these landslides all exhibited not only obvious geomorphological features but also ground motion. A statistical analysis of the topographic and hydrological factors shows that of the detected landslides: 81% are distributed at elevations of 1000–2500 m, over 60% lie within the elevation range of 100~400 m, and 90% present with medium and steep slopes (20°~45°), and 80% are located within areas seeing an annual rainfall of 950~1050 mm. Nine landslides were found to pose potential safety hazards to the expressways. The research findings in this paper have directly benefitted the Sichuan expressways; equally important, it is believed that the technical framework presented in this paper will provide guidance for hazard mitigation and the prevention of transportation hazards in the future.

Landslides are the most serious geological disaster in our country, causing economic losses. Because they go undetected, a large number of landslides that have caused disasters are not in the catalogue. At present, Interferometric Synthetic Aperture Radar (InSAR) has been widely used in the identification of landslides. However, it is time-consuming, inefficient, etc., to survey landslides throughout our large country. In the context of massive SAR data, this problem is more obvious. Therefore, based on the current technique of using differential interferogram phase gradient stacking to avoid phase unwrapping errors, a landslide phase gradient dataset has been constructed. To validate the dataset’s effectiveness and applicability, deep learning methods were introduced, applying the dataset to four networks: U-Net, Attention-Unet, Bisenet v2, and Deeplab v3. The results indicate that the phase gradient dataset performs well across different models, with the Attention-Unet network demonstrating the best performance. Specifically, the precision, recall, and accuracy on the test dataset were 0.8771, 0.8712, and 0.9834, respectively, and the accuracy on the validation dataset was 0.8523. Finally, in this paper, the model is applied to landslide identification in Gansu Province, China, during 2022-2023, and a total of 1882 landslides are found. These landslides are mainly concentrated in the south of Gansu Province, where the terrain is relatively undulating. The results show that this method can quickly and accurately realize landslide automatic identification in a wide area and provide technical support for large-scale landslide disaster surveys.

Pre- event and event landslide deformations have been detected and measured for the landslide that occurred on 3 December 2013 on the south-western slope of the Montescaglioso village (Basilicata Region, southern Italy). In this paper, ground displacements have been mapped through an integrated analysis based on a series of high resolution SAR (Synthetic Aperture Radar) images acquired by the Italian constellation of satellites COSMO-SkyMed. Analysis has been performed by exploiting both phase (through multi-image SAR interferometry) and amplitude information (through speckle tracking techniques) of the satellite images. SAR Interferometry, applied to images taken before the event, revealed a general pre-event movement, in the order of a few mm/yr, in the south-western slope of the Montescaglioso village. Highest pre-event velocities, ranging between 8 and 12 mm/yr, have been recorded in the sector of the slope where the first movement of the landslide took place. Speckle tracking, applied to images acquired before and after the event, allowed the retrieval of the 3D deformation field produced by the landslide. It also showed that ground displacements produced by the landslide have a dominant SSW component, with values exceeding 10 m for large sectors of the landslide area, with local peaks of 20 m in its central and deposit areas. Two minor landslides with a dominant SSE direction, which were detected in the upper parts of the slope, likely also occurred as secondary phenomena as consequence of the SSW movement of the main Montescaglioso landslide. [ABSTRACT FROM AUTHOR]

The region near Dujiangyan City and Wenchuan County, Sichuan China, including significant giant panda habitats, was severely impacted by the Wenchuan earthquake. Largearea landslides occurred and seriously threatened the lives of people and giant pandas. In this paper, we report the development of an enhanced multi-temporal interferometric synthetic aperture radar (MTInSAR) methodology to monitor potential post-seismic landslides by analyzing coherent scatterers (CS) and distributed scatterers (DS) points extracted from multi-temporal L-band ALOS/PALSAR data in an integrated manner. Through the integration of phase optimization and mitigation of the orbit and topography-related phase errors, surface deformations in the study area were derived: the rates in the line of sight (LOS) direction ranged from -7 to 1.5 cm/a. Dozens of potential landslides, distributed mainly along the Minjiang River, Longmenshan Fault, and in other the high-altitude areas were detected. These findings matched the distribution of previous landslides. InSAR-derived results demonstrated that some previous landslides were still active; many unstable slopes have developed, and there are significant probabilities of future massive failures. The impact of landslides on the giant panda habitat, however ranged from low to moderate, would continue to be a concern for conservationists for some time in the future. [ABSTRACT FROM AUTHOR]

Landslide susceptibility assessment (LSA) is an essential tool for landslide hazard warning. The selection of earthquake-related factors is pivotal for seismic LSA. In this study, Newmark displacement (Dn) is employed as the earthquake-related factor, providing a detailed representation of seismic characteristics. On the algorithmic side, a dual-channel convolutional neural network (CNN) model is built, and the last classification layer is replaced with two machine learning (ML) models to facilitate the extraction of deeper features related to landslide development. This research focuses on Beichuan County in Sichuan Province, China. Fifteen landslide predisposing factors, including hydrological, geomorphic, geological, vegetation cover, anthropogenic, and earthquake-related features, were extensively collected. The results demonstrate some specific issues. Dn outperforms conventional earthquake-related factors such as peak ground acceleration (PGA) and Arias intensity (Ia) in capturing seismic influence on landslide development. Under the same conditions, the OA improved by 5.55% and AUC improved by 0.055 compared to the PGA; the OA improved by 3.2% and AUC improved by 0.0327 compared to the Ia. The improved CNN outperforms ML models. Under the same conditions, the OA improved by 4.69% and AUC improved by 0.0467 compared to RF; the OA improved by 4.47% and AUC improved by 0.0447 compared to SVM. Additionally, historical landslides validate the reasonableness of the landslide susceptibility maps. The proposed method exhibits a high rate of overlap with the historical landslide inventory. The proportion of historical landslides in the very high and high susceptibility zones exceeds 87%. The method not only enhances accuracy but also produces a more fine-grained susceptibility map, providing a reliable basis for early warning of seismic landslides. [ABSTRACT FROM AUTHOR]

Conducting landslide recognition research holds notable practical significance for disaster management. In response to the challenges posed by noise, information redundancy, and geometric distortions in single-orbit SAR imagery during landslide recognition, this study proposes a dual-polarization SAR image landslide recognition approach that combines ascending and descending time-series information while considering polarization channel details to enhance the accuracy of landslide identification. The results demonstrate notable improvements in landslide recognition accuracy using the ascending and descending fusion strategy compared to single-orbit data, with F1 scores increasing by 5.19% and 8.82% in Hokkaido and Papua New Guinea, respectively. Additionally, utilizing time-series imagery in Group 2 as opposed to using only pre- and post-event images in Group 4 leads to F1 score improvements of 6.94% and 9.23% in Hokkaido and Papua New Guinea, respectively, confirming the effectiveness of time-series information in enhancing landslide recognition accuracy. Furthermore, employing dual-polarization strategies in Group 4 relative to single-polarization Groups 5 and 6 results in peak F1 score increases of 7.46% and 12.07% in Hokkaido and Papua New Guinea, respectively, demonstrating the feasibility of dual-polarization strategies. However, due to limitations in Sentinel-1 imagery resolution and terrain complexities, omissions and false alarms may arise near landslide edges. The improvements achieved in this study hold critical implications for landslide disaster assessment and provide valuable insights for further enhancing landslide recognition capabilities. [ABSTRACT FROM AUTHOR]

Italy is famous for its one-of-a-kind landscapes and the many cultural heritage sites characterizing the story of its regions. In central Italy, during the medieval age, some of them were built on the top of high and steep cliffs, often on the top of ancient ruins, to protect urban agglomerations, goods and people. The geographical locations of these centers allowed them to maintain their original conformation over time, but, at the same time, exposed them to a high risk of landslides. In this context, this research aimed to present an integrated and low-cost approach to study the potential landslide phenomena affecting two medieval towns. Field surveys and mapping were carried out through the use of innovative digital mapping tools to create a digital database directly on the field. Data gathered during field surveys were integrated with GIS analyses for an improved interpretation of the geological and geomorphological features. Due to the inaccessibility of the cliffs surrounding the two villages, a more detailed analysis of these areas was performed through the use of unmanned aerial vehicle-based photogrammetry, while advanced differential synthetic aperture radar interferometry (A-DInSAR) interpretation was undertaken to verify the stability of the buildings in proximity to the cliffs and other potential active failures. The results of the study highlighted the similar geometry and structural settings of the two areas. Kinematically, the intersection of three main joint sets tends to detach blocks (sometimes in high volumes) from the cliffs. The A-DInSAR analysis demonstrated the presence of a landslide failure along the northwest side of the Monte San Martino town. The buildings in proximity to the cliffs did not show evidence of movements. More generally, this research gives insights into the pro and cons of different survey and analysis approaches and into the benefits of their procedural integration in space and in time. Overall, the procedure developed here may be applied in similar contexts in order to understand the structural features driving slopes' instabilities and create digital databases of geological/monitoring data. [ABSTRACT FROM AUTHOR]

Southeast Asia (SEA) is a region affected by landslide and wildfire; however, few studies on susceptibility modeling for the two hazards together have been conducted for this region, and the intersection and the uncertainty of the two hazards are rarely assessed. Thus, the intersection of landslide and wildfire susceptibility and the spatial uncertainty of the susceptibility maps were studied in this paper. Reliable landslide and wildfire susceptibility maps are necessary for disaster management and land use planning. This work used three advanced ensemble machine learning algorithms: RF (Random Forest), GBDT (Gradient Boosting Decision Tree) and AdaBoost (Adaptive Boosting) to assess the landslide and wildfire susceptibility for SEA. A geo-database was established with 2759 landslide locations, 1633 wildfire locations and 18 predictor variables in total. The performances of the models were assessed using the overall classification accuracy (ACC), Precision, the area under the ROC (receiver operating curve) (AUC) and confusion matrix values. The results showed RF performs superior in both landslide (ACC = 0.81, Precision = 0.78 and AUC= 0.89) and wildfire (ACC= 0.83, Precision = 0.83 and AUC = 0.91) susceptibility modeling, followed by GBDT and AdaBoost. The overall superiority of RF over other models indicates that it is potentially an efficient model for landslide and wildfire susceptibility mapping. The landslide and wildfire susceptibility were obtained using the RF model. This paper also conducted an overlay analysis of the two hazards. The uncertainty of the susceptibility was further assessed using the coefficient of variation (CV). Additionally, the distance to roads is relatively important in both landslide and wildfire susceptibility, which is the most important in landslides and the second most important in wildfires. The result of this paper is useful for mastering the whole situation of hazard susceptibility and proves that RF is a robust model in the hazard susceptibility assessment in SEA.

The Meijiayan landslide in Pengshui County within Chongqing City is a medium-scale soil landslide triggered by the excavation of roadbeds. To delve into the influencing factors and assess the stability of this landslide, it is crucial to meticulously map the subterranean geological framework of the area. Such an analysis lays the groundwork for evaluating and mitigating the risks of future landslide instabilities. In this context, the semi-airborne transient electromagnetic method (SATEM), which is complemented by a receiving system mounted on an aerial platform, stands out as an innovative geophysical exploration technique. This method is adept at conducting swift measurements across complex terrains, making it particularly valuable for areas prone to such geological events. This paper presents the utilization of a cutting-edge loop source SATEM system, which was operationalized via a rotor-based unmanned aerial vehicle (UAV). The system was employed to conduct shallow geological structure detection experiments on the Meijiayan landslide. The SATEM detection outcomes have unveiled fluctuations in the electrical distribution across the upper strata, which are indicative of the subsurface geological boundaries, faults, and areas potentially rich in water within the landslide region. These discoveries affirm the viability of utilizing loop source SATEM for the identification of shallow geological structures in regions susceptible to landslides. The findings indicate that while the landslide is currently in a stable condition, it poses a significant risk of movement, especially during the rainy season, with the potential for landslides to be exacerbated by extreme or sustained rainfall events.

This paper systematically reviews remote sensing technology and learning algorithms in exploring landslides. The work is categorized into four key components: (1) literature search characteristics, (2) geographical distribution and research publication trends, (3) progress of remote sensing and learning algorithms, and (4) application of remote sensing techniques and learning models for landslide susceptibility mapping, detections, prediction, inventory and deformation monitoring, assessment, and extraction and management. The literature selections were based on keyword searches using title/abstract and keywords from Web of Science and Scopus. A total of 186 research articles published between 2011 and 2024 were critically reviewed to provide answers to research questions related to the recent advances in the use of remote sensing technologies combined with artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms. The review revealed that these methods have high efficiency in landslide detection, prediction, monitoring, and hazard mapping. A few current issues were also identified and discussed.

In this paper, we demonstrate the estimation capabilities of landslide reactivation based on various SAR (Synthetic Aperture Radar) methods: Cloude-Pottier decomposition of Sentinel-1 dual polarimetry data, MT-InSAR (Multi-temporal Interferometric Synthetic Aperture Radar) techniques, and cloud computing of backscattering time series. The object of the study is the landslide in the east of Russia that took place on 11 December 2018 on the Bureya River. H-α-A polarimetric decomposition of C-band radar images not detected significant transformations of scattering mechanisms for the surface of the rupture, whereas L-band radar data show changes in scattering mechanisms before and after the main landslide. The assessment of ground displacements along the surface of the rupture in the 2019–2021 snowless periods was carried out using MT-InSAR methods. These displacements were 40 mm/year along the line of sight. The SBAS-InSAR results have allowed us to reveal displacements of great area in 2020 and 2021 snowless periods that were 30–40 mm/year along the line-of-sight. In general, the results obtained by MT-InSAR methods showed, on the one hand, the continuation of displacements along the surface of the rupture and on the other hand, some stabilization of the rate of landslide processes. [ABSTRACT FROM AUTHOR]

Complex and fragile geological conditions combined with periodic fluctuations in reservoir water levels have led to frequent landslide disasters in the Three Gorges Reservoir area. With the development of remote sensing technology, many scholars have applied it to landslide susceptibility assessment to improve model accuracy; however, how to couple these two to obtain the optimal susceptibility assessment model remains to be studied. Based on Sentinel-1 data, relevant data, and existing research results, the information value method (IV), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) models were selected to analyze landslide susceptibility in the urban area of Wanzhou. Models with superior performance will be coupled with PS-InSAR deformation data using two methods: joint training and weighted overlay. The accuracy of different models was assessed and compared with the aim of determining the optimal coupling model and the role of InSAR in the model. The results indicate that the accuracy of different landslide susceptibility prediction models is ranked as RF > SVM > CNN > IV. Among the coupled dynamic models, the performance ranking was as follows: InSAR jointly trained RF (IJRF) > InSAR weighted overlay RF (IWRF) > InSAR jointly trained SVM (IJSVM) > InSAR weighted overlay SVM (IWSVM). Notably, the IJRF model, which combines InSAR deformation data through joint training, exhibited the highest accuracy, with an AUC value of 0.995. In the factor importance analysis within the IJRF model, InSAR deformation data ranked third after hydrological distance (0.210) and elevation (0.163), with a value of 0.154. A comparison between landslide dynamic susceptibility mapping (LDSM) and landslide susceptibility mapping (LSM) revealed that the inclusion of InSAR deformation data effectively reduced false positives around the landslide areas. The results suggest that joint training is the most suitable coupling method, allowing for the optimal expression of InSAR deformation data and enhancing the predictive accuracy of the model. This study serves as a reference for future research and provides a foundation for landslide risk management. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is significant for landslide risk assessment. However, there remains no consensus on which method is optimal for LSM. This study implements a dynamic approach to landslide hazard mapping by integrating spatio-temporal probability analysis with time-varying ground deformation velocity derived from the MT-InSAR (Multi-Temporal InSAR) method. Reliable landslide susceptibility maps (LSMs) can inform landslide risk managers and government officials. First, sixteen factors were selected to construct a causal factor system for LSM. Next, Pearson correlation analysis, multicollinearity analysis, information gain ratio, and GeoDetector methods were applied to remove the least important factors of STI, plan curvature, TRI, and slope length. Subsequently, information quantity (IQ), logistic regression (LR), frequency ratio (FR), artificial neural network (ANN), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) methods were performed to construct the LSM. The results showed that the distance to a river, slope angle, distance from structure, and engineering geological rock group were the main factors controlling landslide development. A comprehensive set of statistical indicators was employed to evaluate these methods' effectiveness; sensitivity, F1-measure, and AUC (area under the curve) were calculated and subsequently compared to assess the performance of the methods. Machine learning methods' training and prediction accuracy were higher than those of statistical methods. The AUC values of the IQ, FR, LR, BP-ANN, RBF-ANN, RF, SVM, and CNN methods were 0.810, 0.854, 0.828, 0.895, 0.916, 0.932, 0.948, and 0.957, respectively. Although the performance order varied for other statistical indicators, overall, the CNN method was the best, while the BP-ANN and RBF-ANN method was the worst among the five examined machine methods. Hence, adopting the CNN approach in this study can enhance LSM accuracy, catering to the needs of planners and government agencies responsible for managing landslide-prone areas and preventing landslide-induced disasters. [ABSTRACT FROM AUTHOR]

The efficiency and accuracy of grid-based computational fluid dynamics methods are strongly dependent on the chosen cell size. The computational time increases exponentially with decreasing cell size. Therefore, a grid coarsing technology without apparent precision loss is essential for various numerical modeling methods. In this article, a physical adaption neural network (PANN) is proposed to optimize coarse grid representation from a fine grid. A new convolutional neural network is constructed to achieve a significant reduction in computational cost while maintaining a relatively accurate solution. An application to numerical modeling of dynamic processes in landslides is firstly carried out, and better results are obtained compared to the baseline method. More applications in various flood scenarios in mountainous areas are then analyzed. It is demonstrated that the proposed PANN downscaling method outperforms other currently widely used downscaling methods. The code is publicly available and can be applied broadly. Computing by PANN is hundreds of times more efficient, meaning that it is significant for the numerical modeling of various complicated Earth-surface flows and their applications. [ABSTRACT FROM AUTHOR]

The Slumgullion landslide is a large translational debris slide whose currently active part has likely been sliding for approximately 300 years. Its permanent motion and evolutionary processes have attracted the attention of many researchers. In order to study its mass wasting processes and evolution trend, the spatial–temporal displacement of the Slumgullion landslide was retrieved using an adaptive pixel offset tracking (POT) method with multi-track Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) images. Based on three-dimensional displacement and slope information, we then revealed the spatial–temporal distribution of surface mass depletion or accumulation in the landslide, which provides a new perspective to analyze the evolutionary processes of landslides. The results indicate that the Slumgullion landslide had a spatially variable displacement, with a maximum displacement of 35 m. The novel findings of this study mainly include two parts. First, we found that the surface mass accumulated in the toe of the landslide and depleted in the top and middle area during the interval, which could increase the resisting force and decrease the driving force of the Slumgullion landslide. This result is compelling evidence which indicates the Slumgullion landslide should eventually tend to be stable. Second, we found that the distribution of geological structures can well explain some of the unique mass wasting in the Slumgullion landslide. The larger local mass depletion in the landslide neck area verifies that the sharp velocity increase in this region is not only caused by the reduction in width but is also significantly affected by the local normal faults. In summary, this study provides an insight into the relation between the landslide motion, mass volume change, and geological structure. The results demonstrate the great potential of multi-track airborne SAR for displacement monitoring and evolutionary analysis of landslides. [ABSTRACT FROM AUTHOR]

Seismic landslides are the most common and highly destructive earthquake-triggered geological hazards. They are large in scale and occur simultaneously in many places. Therefore, obtaining landslide information quickly after an earthquake is the key to disaster mitigation and relief. The survey results show that most of the landslide-information extraction methods involve too much manual participation, resulting in a low degree of automation and the inability to provide effective information for earthquake rescue in time. In order to solve the abovementioned problems and improve the efficiency of landslide identification, this paper proposes an automatic landslide identification method named improved U-Net model. The intelligent extraction of post-earthquake landslide information is realized through the automatic extraction of hierarchical features. The main innovations of this paper include the following: (1) On the basis of the three RGB bands, three new bands, DSM, slope, and aspect, with spatial information are added, and the number of feature parameters of the training samples is increased. (2) The U-Net model structure is rebuilt by adding residual learning units during the up-sampling and down-sampling processes, to solve the problem that the traditional U-Net model cannot fully extract the characteristics of the six-channel landslide for its shallow structure. At the end of the paper, the new method is used in Jiuzhaigou County, Sichuan Province, China. The results show that the accuracy of the new method is 91.3%, which is 13.8% higher than the traditional U-Net model. It is proved that the new method is effective and feasible for the automatic extraction of post-earthquake landslides.

This study focuses on the Kuibyshev reservoir (Volga River basin, Russia)—the largest in Eurasia and the third in the world by area (6150 km2). The objective of this paper is to quantitatively assess the dynamics of reservoir bank landslides and shoreline abrasion at active zones based on the integrated use of modern instrumental methods (i.e., terrestrial laser scanning—TLS, unmanned aerial vehicle—UAV, and a global navigation satellite system—GNSS) and GIS analysis of historical imagery. A methodology for the application of different methods of instrumental assessment of abrasion and landslide processes is developed. Different approaches are used to assess the intensity of landslide and abrasion processes: the specific volume and material loss index, the planar displacement of the bank scarp, and the planar-altitude analysis of displaced soil material based on the analysis of slope profiles. Historical shoreline position (1958, 1985, and 1987) was obtained from archival aerial photo data, whereas data for 1975, 1993, 2010, 2011, and 2012 were obtained from high-resolution satellite image interpretation. Field surveys of the geomorphic processes from 2002, 2003, 2005, 2006, 2014 were carried out using Trimble M3 and Trimble VX total stations; in 2012–2014 and 2019 TLS and UAV surveys were made, respectively. The monitoring of landslide processes showed that the rate of volumetric changes at Site 1 remained rather stable during the measurement period with net material losses of 0.03–0.04 m−3 m−2 yr−1. The most significant contribution to the average annual value of the material loss was snowmelt runoff. The landslide scarp retreat rate at Site 2 showed a steady decreasing trend, due to partial overgrowth of the landslide accumulation zone resulting in its relative stabilization. The average long-term landslide scarp retreat rate is—2.3 m yr−1. In 2019 earthworks for landscaping at this site have reduced the landslide intensity by more than 2.5 times to—0.84 m yr−1. [ABSTRACT FROM AUTHOR]

Slow to extremely slow landslides in urban areas may cause severe damage to buildings and infrastructure that can lead to the evacuation of local populations in case of slope accelerations. Monitoring the spatial and temporal evolution of this type of natural hazard represents a major concern for the public authorities in charge of risk management. Pariana, a village with 400 residents located in the Apuan Alps (Massa, Tuscany, Italy), is an example of urban settlement where the population has long been forced to live with considerable slope instability. In the last 30 years, due to the slope movements associated with a slow-moving landslide that has affected a significant portion of the built-up area, several buildings have been damaged, including a school and the provincial road crossing the unstable area, leading to the need for an installation of a slope monitoring system with early warning capabilities, in parallel with the implementation of mitigation works. In this paper, we show how satellite multi-temporal interferometric synthetic aperture radar (MT-InSAR) data can be effectively used when coupled with a wireless sensor network made of several bar extensometers and a borehole inclinometer. In fact, thanks to their wide area coverage and opportunistic nature, satellite InSAR data allow one to clearly identify the spatial distribution of surface movements and their long-term temporal evolution. On the other hand, geotechnical sensors installed on specific elements at risk (e.g., private buildings, retaining walls, etc.), and collected through Wi-Fi dataloggers, provide near real-time data that can be used to identify sudden accelerations in slope movements, subsequently triggering alarms. The integration of those two-monitoring systems has been tested and assessed in Pariana. Results show how a hybrid slope monitoring program based on the two different technologies can be used to effectively monitor slow-moving landslides and to identify sudden accelerations and activate a response plan. [ABSTRACT FROM AUTHOR]

Triggered by earthquakes, rainfall, or anthropogenic activities, landslides represent widespread and problematic geohazards worldwide. In recent years, multiple remote sensing techniques, including synthetic aperture radar, optical, and light detection and ranging measurements from spaceborne, airborne, and ground-based platforms, have been widely applied for the analysis of landslide processes. Current techniques include landslide detection, inventory mapping, surface deformation monitoring, trigger factor analysis and mechanism inversion. In addition, landslide susceptibility modelling, hazard assessment, and risk evaluation can be further analyzed using a synergic fusion of multiple remote sensing data and other factors affecting landslides. We summarize the 19 articles collected in this special issue of Remote Sensing of Landslide, in the terms of data, methods and applications used in the papers. [ABSTRACT FROM AUTHOR]

Spaceborne interferometric synthetic aperture radar (InSAR) techniques are important for landslide detection and monitoring; however, several limitations and uncertainties, such as the unique north–south flying direction and side-look radar observing geometry, currently limit the ability of InSAR to credibly detect landslides, especially those related to high and steep slopes. Here, we conducted experimental and statistical analysis on the feasibility of time-series InSAR monitoring for steep slopes using ascending and descending SAR images. First, the theoretical (TGNSS), practical (PGNSS), and terrain (Hterrain) (T-P-H) indices for sensitivity evaluations of the slope displacement monitoring results from time-series InSAR were proposed for slope monitoring. Subsequently, two experimental and statistical studies were conducted for the cases with and without Global Navigation Satellite System (GNSS) monitoring data. Our experimental results of two high and steep open-pit mines showed that the defined theoretical and practical sensitivity indices can quantitatively evaluate the feasibility of ascending and descending InSAR observations in steep-slope deformation monitoring with GNSS data, and the terrain sensitivity index can qualitatively evaluate the feasibility of landslide monitoring results from ascending and descending Sentinel-1 satellite data without GNSS data. We further demonstrate the generalizability of these proposed indices using four landslide cases with both public GNSS and InSAR monitoring data and 119 landslide cases with only InSAR monitoring data. The statistical results indicated that greater indices correlated with higher reliability of the monitoring results, suggesting that these novel indices have wide suitability and applicability. This study can help to improve the practice of slope deformation monitoring using spaceborne InSAR, especially for high and steep slopes. [ABSTRACT FROM AUTHOR]

This study explored the applicability of TRMM, TRMM nonlinear downscaling, and ANUSPLIN (ANU) interpolation of three different types of precipitation data to define regional-scale rainfall-triggered landslide thresholds. The spatial resolution of TRMM precipitation data was downscaled from 0.25° to 500 m by the downscaling model considering the relationship between humidity, NDVI, and numerous topographic factors and precipitation. The rainfall threshold was calculated using the rainfall intensity–duration threshold model. The calculation showed that TRMM downscaled precipitation data have better detection capability for extreme precipitation events than the other two, the TRMM downscaling threshold was better than the ANU interpolation, and the cumulative effective rainfall of TRMM downscaling was preferred as the macroscopic critical rainfall-triggered landslide threshold for the early warning of the Wudu. The predictive performance of the rainfall threshold of 50% was better than the other two (10% and 90%). When the probability of landslide occurrence was 50%, the TRMM downscaled threshold curve was given by I 50 = 21.03 × D − 1.004 . The authors also analyzed the influence of factors such as topography landform and soil type on the rainfall threshold of landslides in the study area. The rainfall intensity of small undulating mountains was higher than that of medium and large undulating mountains, and the rainfall intensity of landslides peaks at high altitude mountains of 3500–5000 m. [ABSTRACT FROM AUTHOR]

The extraction of underground minerals in hilly regions is highly susceptible to landslides, which requires the application of InSAR techniques to monitor the surface displacement. However, repeated mining for multiple coal seams can cause a large displacement beyond the detectable gradient of the traditional InSAR technique, making it difficult to explore the relationship between landslides and subsurface excavations in both temporal and spatial domains. In this study, the Tengqing landslide in Shuicheng, Guizhou, China, was chosen as the study area. Firstly, the large-gradient surface displacement in the line of sight was obtained by the fusion of SAR offset tracking and interferometric phase. Subsequently, a multi-segment logistic model was proposed to simulate the temporal effect induced by repeated mining activities. Next, a simplified probability integral method (SPIM) was utilized to invert the geometry of the mining tunnel and separate the displacement of the mining subsidence and landslide. Finally, the subsurface mining parameters and in situ investigation were carried out to assess the impact of mining and precipitation on the kinematic process of Tengqing landslides. Results showed that the repeated mining activities in Tengqing can not only cause land subsidence and rock avalanches at the top of the mountain, but also accelerate the landslide displacement. The technical approach presented in this study can provide new insights for monitoring and modeling the effects of repeated mining-induced landslides in mountainous areas. [ABSTRACT FROM AUTHOR]