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.

Accurate landslide detection and mapping are essential for land use planning, management/assessment, and geo-disaster risk mitigation as well as post disaster reconstructions. Till now, visual interpretation and field survey are still the most widely adopted techniques for landslide mapping, which are often criticized labor-intensive, time consuming and costly. With the rapid advancement of artificial intelligence, deep-learning-based approach for landslide detection and mapping has drawn great attention for its significant advantages over the traditional techniques. However, lack of sufficient training samples has constrained the application of deep-learning-based approach in landslide detection from satellite images for a long time. The present study aimed to examine the feasibility of a new deep-learning-based approach to intelligently detect and map earthquake-triggered landslides from single-temporal RapidEye satellite images. Specifically, the proposed approach consists of three steps. First of all, a standard data pre-processing workflow to automatically generate training samples was designed and some data augmentation strategies were implemented to alleviate the lack of training samples. Then, a cascaded end-to-end deep learning network, namely LandsNet, was constructed to learn various features of landslides. Finally, the identified landslide maps were further optimized with morphological processing. Experiments in two spatially independent earthquake-affected regions showed our proposed approach yielded the best F1 value of about 86.89%, which was about 7% and 8% higher than that obtained by ResUNet and DeepUNet, respectively. Comparative studies on the feasibility and robustness of the proposed approach with ResUNet and DeepUNet demonstrated its strong application potentials in the emergency response of natural disasters.

A M_w=6.5 earthquake struck the Jiuzhaigou region of Sichuan Province, China, at 21:19 LT on Tuesday, 8 August 2017, and triggered a large number of landslides. For mitigating the damages of earthquake-triggered landslides to individuals and infrastructures of the earthquake-affected region, a comprehensive landslide susceptibility mapping was attempted with an integrated weighted index model by combining the frequency ratio and the analytical hierarchy process approaches under a GIS-based environment in the heavily earthquake-affected Zhangzha town of the Jiuzhaigou region. For this purpose, a total number of 842 earthquake-triggered landslides were visually interpreted and located from Sentinel-2A images acquired before and after the earthquake at first, and then the recognized landslides were randomly split into two groups to establish the earthquake-triggered landslide inventory, among which 80 % of the landslides were used for training the integrated model and the remaining 20 % for validation. Nine landslide controlling factors were considered including slope, aspect, elevation, lithology, distance from faults, distance from rivers, land use–land cover, normalized difference vegetation index and peak ground acceleration. The frequency ratio was utilized to evaluate the contribution of each landslide controlling factor to landslide occurrence, and the analytical hierarchy process was used to analyse the mutual relationship between landslide controlling factors. Finally, the landslide susceptibility map was produced by using weighted overlay analysis. Furthermore, an area under the curve approach was adopted to comprehensively evaluate the performance of the integrated weighted index model, including the degree of model fit and model predictive capability. The results demonstrated the reliability and feasibility of the integrated weighted index model in earthquake-triggered landslide susceptibility mapping at a regional scale. The generated map can help engineers and decision makers assess and mitigate hazards of the earthquake-triggered landslides to individuals and infrastructures of the earthquake-affected region.

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.

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.