Search

The increasing number of landslide hazards worldwide has placed greater demands on the production and updating of landslide inventory maps. As an important data source for landslide detection, interferometric synthetic aperture radar (InSAR) data processing is time-consuming and also requires specialized knowledge, which severely hinders its widespread application. At present, a new cloud-based online platform, i.e., Alaska Satellite Facility's Hybrid Pluggable Processing Pipeline (ASF HyP3) was developed for massive SAR data processing. In this study, combining the HyP3 online platform and Stacking-InSAR method, we constructed a new easy-to-use processing chain for rapidly identifying slow-moving landslides over large areas. With this processing chain, a total of 923 interferometric pairs covering an area of over 1800 km2 were processed within a few hours (about 4 to 5 h). A total of 81 slow-moving landslides were immediately detected and mapped using Stacking-InSAR method, of which 65 landslides were confirmed by previous studies and 16 landslides were newly detected. Results show that the new processing chain can greatly improve the efficiency of wide-area landslide mapping and is expected to serve as an effective tool for rapid updating the existing landslide inventories and contribute to the prevention and management of geological hazards. [ABSTRACT FROM AUTHOR]

Due to various factors such as urban development, climate change, and tectonic movements, landslides are a common geological phenomenon in the Qinghai–Tibet Plateau region, especially on both sides of a road, where large landslide hazards often result in traffic disruptions and casualties. Identifying the spatial distribution of landslides and monitoring their stability are essential for predicting landslide occurrence and implementing prevention measures. In this study, taking the Kangding-Batang section of Shanghai-Nyalam Road as the study area, we adopted a semi-automated time-series interferometric synthetic aperture radar (InSAR) method to identify landslides and monitor their activity. A total of 446 Sentinel-1 ascending and descending SAR images from January 2018 to December 2021 were thus collected and processed by using open-source InSAR processing software. After a series of error corrections, we obtained surface deformation maps covering the study area, and a total of 236 potential landslides were subsequently identified and classified into three categories, namely slow-sliding rockslides, debris flows, and debris avalanches, by combining deformation maps, optical images, and a digital elevation model (DEM). For a typical landslide, we performed deformation decomposition and analyzed the relationship between its deformation and rainfall, revealing the contribution of rainfall to the landslide. In addition, we discussed the effect of SAR geometric distortion on landslide detection, highlighting the importance of joint ascending and descending observations in mountainous areas. We analyzed the controlling factors of landslide distribution and found that topographic conditions are still the dominant factor. Our results may be beneficial for road maintenance and disaster mitigation. Moreover, the entire processing is semi-automated based on open-source tools or software, which provides a paradigm for landslide-related studies in other mountainous regions of the world. [ABSTRACT FROM AUTHOR]

Identifying and assessing the disaster risk of landslide-prone regions is very critical for disaster prevention and mitigation. Owning to their special advantages, neural network algorithms have been widely used for landslide susceptibility mapping (LSM) in recent decades. In the present study, three advanced neural network models popularly used in relevant studies, i.e. artificial neural network (ANN), one dimensional convolutional neural network (1D CNN) and recurrent neural network (RNN), were evaluated and compared for LSM practice over the Qingchuan County, Sichuan province, China. Extensive experimental results demonstrated satisfactory performances of these three neural network models in accurately predicting susceptible regions. Specifically, ANN and 1D CNN models yielded quite consistent LSM results but slightly differed from those of RNN model spatially. Nevertheless, accuracy evaluations revealed that the RNN model outperformed the other two models both qualitatively and quantitatively but its complexity was relatively high. Experiments concerning training hyper-parameters on the performance of neural network models for LSM suggested that relatively small batch size values with Tanh activation function and SGD optimizer are essential to improve the performance of neural network models for LSM, which may provide a thread to help those who apply these advanced algorithms to improve their efficiency. [ABSTRACT FROM AUTHOR]

Until the Mw 6.6 Luding earthquake ruptured the Moxi section of the Xianshuihe fault (XSHF) on 5 September 2022, the region had not experienced an Mw >6 earthquake since instrumental records began. We used Global Positioning System (GPS) and Sentinel-1 interferometric synthetic aperture radar (InSAR) observations to image the coseismic deformation and constrain the location and geometry of the seismogenic fault using a Bayesian method We then present a distributed slip model of the 2022 Mw6.6 Luding earthquake, a left-lateral strike-slip earthquake that occurred on the Moxi section of the Xianshuihe fault in the southwest Sichuan basin, China. Two tracks (T26 and T135) of the InSAR data captured a part of the coseismic surface deformation with the line-of-sight displacements range from ∼−0.16 m to ~0.14 m in the ascending track and from ~−0.12 m to ~0.10 m in the descending track. The inverted best-fitting fault model shows a pure sinistral strike-slip motion on a west-dipping fault plane with a strike of 164.3°. We adopt a variational Bayesian approach and account for the uncertainties in the fault geometry to retrieve the distributed slip model. The inverted result shows that the maximum slip of ~1.82 m occurred at a depth of 5.3 km, with the major slip concentrated within depths ranging from 0.9–11 km. The InSAR-determined moment is 1.3 × 1019 Nm, with a shear modulus of 30 GPa, equivalent to Mw 6.7. The published coseismic slip models of the 2022 Luding earthquake show apparent differences despite the use of similar geodetic or seismic observations. These variations underscore the uncertainty associated with routinely performed source inversions and their interpretations for the underlying fault model. [ABSTRACT FROM AUTHOR]

On 2015 November 4, an M w 6.5 earthquake struck the east region of Alor Island, eastern Indonesia. Here, we use Sentinel-1 and ALOS-2 data to explore the coseismic surface displacement of this earthquake. Based on the ALOS-2 coseismic interferograms, the first fault model and coseismic slip distribution of the 2015 Alor earthquake are presented in this study. The preferred slip model links to a blind south-southeast striking, south-southwest dipping strike-slip fault with amount of normal slip component and a peak slip of 2.09 m at 2.34 km of depth. Considering the fact that the ascending and descending InSAR prediction of the distributed slip model does not fit the InSAR observations at the northwest and southeast tips with the simple planar fault model. We tried to construct a strike-variable fault model to further improve data fit. The results of the calculated Coulomb stress change imply that the regions with positive CFS changes mainly located at the northwest and southeast extremities of the rupture of the Alor earthquake, and in the lobes north and south of the rupture. The most striking discovery from the InSAR observations of the Alor earthquake is that most of the displacements occurred on a fault whose existence was unknown before the earthquake. [ABSTRACT FROM AUTHOR]

• A CNN-based approach was applied to map the landslide susceptibility. • A novel multiscale sampling strategy was proposed to generate the training data. • Three machine learning methods were applied for comparison. • CNN trained with multiscale fusion data can generate accurate and reliable results. Landslides are one of the most widespread natural disasters and pose severe threats to people, properties, and the environment in many areas. Landslide susceptibility mapping (LSM) has proven useful in designing landslide mitigation strategies for reducing disaster risk and societal and economic losses, which are essential for land use planning, hazard prevention, and risk management. Recent efforts for improving accuracies of LSM have focused on the utilization of convolutional neural network (CNN) in some image-related tasks, however, due to the inconsistency of data representation, CNN-related studies need to be further explored. In this study, a CNN-based approach for LSM was proposed and experimentally applied in a Jiuzhaigou region where a catastrophic earthquake taken place on 8 August 2017, in Sichuan, China. To address the issue of data representation in the CNN model, we proposed a multiscale sampling strategy which to our knowledge is novel in LSM. In this way, the multiscale training samples (i.e., small scale, medium scale and large scale) were generated from the selected eleven landslide causative factors. The success-rate curve (SRC) and prediction-rate curve (PRC) were applied to validate the LSM results, and three conventional machine learning algorithms, i.e., logistic regression, multi-layer perceptron (MLP) neural network and radial basis function (RBF) neural network, were attempted for comparison. Specifically, MLP neural network achieved the best performance among three machine learning methods, with the area under the SRC (AU-SRC) and PRC (AU-PRC) values of 81.18% and 82.84%, respectively. Nevertheless, the AU-SRC and AU-PRC values of CNN-based approach reached to 97.45% and 88.02%, which were about 16% and 6% higher than that of the MLP neural network, respectively. The present study demonstrated both the excellent goodness-of-fit and strong prediction ability of CNN-based approach for LSM, which also showed the effectiveness and feasibility of the proposed multiscale sampling strategy. Additionally, present study revealed that the spatial data close to the landslide location might be more suitable to predict the probability of the landslide occurrence. Finally, we expect that the deep learning method based on multiscale data representation will advance our ability to assess the landslide susceptibility and raise the awareness of landslide disasters. [ABSTRACT FROM AUTHOR]

Urban building segmentation is a prevalent research domain for very high resolution (VHR) remote sensing; however, various appearances and complicated background of VHR remote sensing imagery make accurate semantic segmentation of urban buildings a challenge in relevant applications. Following the basic architecture of U-Net, an end-to-end deep convolutional neural network (denoted as DeepResUnet) was proposed, which can effectively perform urban building segmentation at pixel scale from VHR imagery and generate accurate segmentation results. The method contains two sub-networks: One is a cascade down-sampling network for extracting feature maps of buildings from the VHR image, and the other is an up-sampling network for reconstructing those extracted feature maps back to the same size of the input VHR image. The deep residual learning approach was adopted to facilitate training in order to alleviate the degradation problem that often occurred in the model training process. The proposed DeepResUnet was tested with aerial images with a spatial resolution of 0.075 m and was compared in performance under the exact same conditions with six other state-of-the-art networks—FCN-8s, SegNet, DeconvNet, U-Net, ResUNet and DeepUNet. Results of extensive experiments indicated that the proposed DeepResUnet outperformed the other six existing networks in semantic segmentation of urban buildings in terms of visual and quantitative evaluation, especially in labeling irregular-shape and small-size buildings with higher accuracy and entirety. Compared with the U-Net, the F1 score, Kappa coefficient and overall accuracy of DeepResUnet were improved by 3.52%, 4.67% and 1.72%, respectively. Moreover, the proposed DeepResUnet required much fewer parameters than the U-Net, highlighting its significant improvement among U-Net applications. Nevertheless, the inference time of DeepResUnet is slightly longer than that of the U-Net, which is subject to further improvement. [ABSTRACT FROM AUTHOR]

The identification and early warning of potential landslides can effectively reduce the number of casualties and the amount of property loss. At present, interferometric synthetic aperture radar (InSAR) is considered one of the mainstream methods for the large-scale identification and detection of potential landslides, and it can obtain long-term time-series surface deformation data. However, the method of identifying anomalous deformation areas using InSAR data is still mainly manual delineation, which is time-consuming, labor-consuming, and has no generally accepted criterion. In this study, a two-stage detection deep learning network (InSARNet) is proposed and used to detect anomalous deformation areas in Maoxian County, Sichuan Province. Compared with the most commonly used detection models, it is demonstrated that the InSARNet has a better performance in the detection of anomalous deformation in mountainous areas, and all of the quantitative evaluation indexes are higher for InSARNet than for the other models. After the anomalous deformation areas are identified using the proposed model, the possible relationship between the anomalous deformation areas and potential landslides is investigated. Finally, the fact that the automatic and rapid identification of potential landslides is the inevitable trend of future development is discussed. [ABSTRACT FROM AUTHOR]

Accurate delineation of spatiotemporal variations in ground surface soil freeze and thaw (F/T) states is essential to appraise many geoscience issues, such as the hydrological circulation and land surface-atmosphere feedbacks. Recently, an Improved Dual-index algorithm (DIA) method was proposed by accounting for the influence of soil moisture variations on the discrimination accuracy with passive microwave remote sensing (RS) data products. Compared with the original DIA, the Improved DIA method has proven to be a more practical approach on surface soil F/T states discrimination. However, the method has only been applied and verified in cold regions of high-altitude (e.g., Tibetan Plateau), it's applicability and effectiveness in the cold areas in mid-high latitudes, where the geographic and climatic conditions are quite different, yet remained to be further explored. The present study investigated the feasibility of using AMSR-E (the Advanced Microwave Scanning Radiometer-EOS) and AMSR2 (the second Advance Microwave Scanning Radiometer) passive microwave RS data products to discriminate the F/T states of the ground surface for a long period from 2002 to 2019 by means of the Improved DIA method over a typical mid-high latitude cold region of Northeastern China. Seasonal variation characteristics of soil moisture in mid-high latitude areas were similar with those in high-altitude areas, even though the spatial heterogeneity of soil water content was significant in different regions. Discriminating surface soil F/T states with the Improved DIA method derived overall discriminating accuracy of about 91.6% in the study area, which demonstrated excellent feasibility of the Improved DIA method in mid-high latitude cold regions. The mapping results shown surface soil F/T cycle in Northeastern China responding to climate change was examined from the perspective of regional average, both the proportion of frozen soil area and frozen days showed significant decreasing trends continuously with differed quite spatially. The discriminating accuracy of the Improved DIA method was found to be lower in plain areas with dense populations and large farmland areas compared to mountainous areas when human activities were not taken into consideration, as quantifying human activities can be challenging. The Improved DIA method has been well verified in both high-altitude and high-latitude regions; it has great potential in global scale research. • The Improved DIA method derived accuracy of about 91.6% in Northeastern China. • The accuracy of the Improved DIA method is greatly affected by human activities. • The frozen soil in Northeastern China has been serious degradation in past decades. [ABSTRACT FROM AUTHOR]

[Display omitted] • A fully distributed frozen soil hydrothermal processes model was developed. • The hydrological impacts of surface soil freeze-thaw cycle were quantified. • Soil ice meltwater contributing to watershed reached about 35% in thawing period. The freeze–thaw cycle over the surface seasonally frozen soil is an important soil hydrothermal dynamic process linking land surface processes and climatic changes in the cold regions. With the advancement of frozen soil hydrothermal dynamic studies and remote sensing technology, the simulation of frozen soil hydrological processes based on the distributed numerical model has become a hotspot to better understand the impact of frozen soil hydrothermal dynamics on the watershed hydrological processes in the cold regions over a large spatial scale. However, the quantitative analysis of the impact of seasonally frozen soil hydrothermal processes on watershed runoff at long-term time scales remained an unsolved issue in the field of frozen soil hydrology. Under the framework of the watershed distributed eco-hydrological model ESSI-3, a fully distributed frozen soil hydro-thermal processes integrated modeling system (FFIMS model) was established based on the coupled water and heat transferring mechanism for frozen soil hydro-thermal process simulations in the frozen surface or at a certain depth of a watershed. By coupling the FFIMS model with the distributed eco-hydrological model ESSI-3, the impacts of seasonally frozen soil hydrothermal processes on hydrological processes were investigated from the perspective of temporal-spatial domain with the simulated hydrothermal and hydrological processes for a long-term period from 2008 to 2016 over a watershed located in the cold region of Northeastern China. The results suggested that the soil freeze–thaw cycling posed different impacts with limited significance throughout the whole hydrological processes of the watershed in different seasons. Significant impacts on the hydrological processes were particularly observed in the thawing period of a year, when soil ice meltwater contributing to the discharge of the study watershed reached to about 35% in average in this period. ESSI-3 coupled with the FFIMS modelling system obviously improved the performance of the original ESSI-3 in cold region watershed simulations, and the averaged Nash efficiency coefficients obtained increased from almost 0 to 0.77 in the thawing period of a year. The study demonstrated the importance of application of spatially distributed numerical model with physical mechanism for seasonally frozen soil water and heat transfer process simulations. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) is capable of automatically extracting image features and has been widely used in remote sensing image classifications. Feature extraction is an important and difficult problem in current research. In this paper, data augmentation for avoiding over fitting was attempted to enrich features of samples to improve the performance of a newly proposed convolutional neural network with UC-Merced and RSI-CB datasets for remotely sensed scene classifications. A multiple grouped convolutional neural network (MGCNN) for self-learning that is capable of promoting the efficiency of CNN was proposed, and the method of grouping multiple convolutional layers capable of being applied elsewhere as a plug-in model was developed. Meanwhile, a hyper-parameter C in MGCNN is introduced to probe into the influence of different grouping strategies for feature extraction. Experiments on the two selected datasets, the RSI-CB dataset and UC-Merced dataset, were carried out to verify the effectiveness of this newly proposed convolutional neural network, the accuracy obtained by MGCNN was 2% higher than the ResNet-50. An algorithm of attention mechanism was thus adopted and incorporated into grouping processes and a multiple grouped attention convolutional neural network (MGCNN-A) was therefore constructed to enhance the generalization capability of MGCNN. The additional experiments indicate that the incorporation of the attention mechanism to MGCNN slightly improved the accuracy of scene classification, but the robustness of the proposed network was enhanced considerably in remote sensing image classifications. [ABSTRACT FROM AUTHOR]