Landslide inventory mapping (LIM) is a key prerequisite for landslide susceptibility evaluation and disaster mitigation. It aims to record the location, size, and extent of landslides in each map scale. Machine learning algorithms, such as support vector machine (SVM) and random forest (RF), have been increasingly applied to landslide detection using remote sensing images in recent decades. However, their limitations have impeded their wide application. Furthermore, despite the widespread use of deep learning algorithms in remote sensing, for LIM, deep learning algorithms are limited to less unbalanced landslide samples. To this end, in this study, full convolution networks with focus loss (FCN-FL) were adopted to map historical landslides in regions with imbalanced samples using an improved symmetrically connected full convolution network and focus loss function to increase the feature level and reduce the contribution of the background loss value. In addition, K-fold cross-validation training models (FCN-FLK) were used to improve data utilization and model robustness. Results showed that the recall rate, F1-score, and mIoU of the model were improved by 0.08, 0.09, and 0.15, respectively, compared to FCN. It also demonstrated advantages over U-Net and SegNet. The results prove that the method proposed in this study can solve the problem of imbalanced sample in landslide inventory mapping. This research provides a reference for addressing imbalanced samples in the deep learning of LIM.

Interferometric Synthetic Aperture Radar (InSAR) technology is the most advanced and effective method for monitoring large-scale slow-moving landslides. However, automatic landslide detection based on InSAR products regarding landslide samples and deep learning models is still challenging. Different InSAR products are inconsistent for slow-moving landslide detection due to the fuzzy boundaries of potential landslides and complex deformation characteristics. In addition, the accuracy of existing landslide detection models is not high because multi-scale factors in feature abstract and feature fusion are rarely considered. This paper proposes a multi-scale Swin Transformer InSAR products detection network (MSIDNet) to detect slow-moving landslides automatically. Firstly, we adopt an advanced Swin Transformer as the backbone to extract features and multi-scale spatial-temporal attention blocks in the neck to improve the feature fusion capability. Meanwhile, to train the new model, we built a landslide dataset based on visual interpretation, including deformation rate, phase gradient, and C-index (GRCI). Experiments demonstrate that our proposed method outperforms the existing deep learning models like Faster R-CNN and Yolov3. The GRCI dataset is more efficient and less biased than the traditional deformation rate and phase gradient datasets. The precision of detected landslides in a given testing area is 0.89, and it has good generalization ability. This study provides a new dataset and method for slow-moving landslide detection based on InSAR products.

Landslide inventory mapping (LIM) is an important prerequisite for disaster emergency rescue and landslide sensitivity analysis. It has been proven that convolutional neural networks have better performance for LIM than traditional machine learning methods such as support vector machines (SVM), and random forests (RF). However, the accuracy of existing methods based only on optical images is low due to the complex landslide background. Moreover, the multi-scale features of landslides are not considered in convolutional neural network methods. Therefore, this study proposes Multi-featured independent component analysis UNet3+ (MICUNet3+) for landslide inventory mapping based on optical images, which combines co-feature, independent component analysis (ICA), and UNet3+. Firstly, normalized difference vegetation index (NDVI) and gray level co-occurrence matrix (GLCM) are extracted from remote sensing images acquired pre- and post- earthquake event and then processed by change vector analysis. Then, ICA is implemented for NDVI, GLCM, and three elevation factors. Lastly, the three principal components and the post-event images are fed into UNet3+ to generate LIM by multi-scale features and deep supervision. Finally, we validate the proposed method by using the co-seismic landslide of Jiuzhaigou earthquake as an experiment. The results show that the performance of recall, F1-score and mIoU are 0.13, 0.22 and 0.11 higher than those of the post-event-only images, respectively, indicating that the proposed method can effectively solve the problems of landslide identification in terms of multi-scale features and complex background.

Global assessments of landslide impact on critical communication infrastructure have become urgent because of rising occurrences related to human activities and climate change. The landslide and glacial slide susceptibility along the Karakoram Highway poses a significant threat to the infrastructure ecosystem, local communities, and the critical China–Pakistan Economic Corridor. This research paper utilized the Small Baseline Subset InSAR technique to monitor the deformation patterns over the past 5 years, yielding high-resolution insights into the terrain instability in this geologically active region. The SBAS time series results reveal that the substantial cumulative deformation in our study area ranges from 203 mm to −486 mm, with annual deformation rates spanning from 62 mm/year to −104 mm/year. Notably, the deformation that occurred is mainly concentrated in the northern section of our study area. The slope’s aspect is responsible for the maximum deformed material flow towards the Karakoram Highway via steep slopes, lost glacial formations, and the climate variations that cause the instability of the terrain. The given pattern suggests that the northern area of the Karakoram Highway is exposed to a greater risk from the combined influence of glacial slides, landslides, and climatic shifts, which call for the increased monitoring of the Karakoram Highway. The SBAS-InSAR method is first-rate in deformation monitoring, and it provides a scientific basis for developing real-time landslide monitoring systems. The line of sight limitations and the complexity and imprecision of weather-induced signal degradation should be balanced through additional data sources, such as field surveys to conduct large slide and glacial slide susceptibility evaluations. These research results support proactive hazard mitigation and infrastructure planning along the China–Pakistan Economic Corridor by incorporating SBAS-InSAR monitoring into the original planning. The country’s trade policymakers and national level engineers can enhance transport resilience, efficiently manage the landslide and glacial slide risks, and guarantee safer infrastructure along this strategic trade route.

Preparation of Nanocellulose with Cation–Exchange Resin Catalysed Hydrolysis | InTechOpen, Published on: 2011-09-15. Authors: Huang Biao, Tang Li-rong, Dai Da-song, et