Valuable Clues for DCNN-Based Landslide Detection from a Comparative Assessment in the Wenchuan Earthquake Area

ResM-FusionNet for efficient landslide detection algorithm with a hybrid architecture

Landslides, as a prevalent geological hazard, pose a severe threat to both the environment and human society. The rapid and accurate identification of landslide-prone areas is crucial for disaster response, risk assessment, and urban planning. This paper proposes a novel deep learning-based landslide detection method ResM-FusionNet, which leverages ResNet-50 as the backbone for feature extraction and integrates a multi-layer perceptron as the decoder to enhance segmentation accuracy. To address the challenges of complex terrain and boundary detail detection in landslide-prone regions, we introduce a novel loss function, RLoss, which integrates masking mechanisms, semantic weighting, and a Top-K pixel loss averaging strategy. Experimental results on remote sensing datasets demonstrate that ResM-FusionNet significantly outperforms existing models. Specifically, ResM-FusionNet achieves 94.33% accuracy, 85.73% F1-score, and a Kappa coefficient of 70.12%, surpassing other models (e.g., SegFormer, DeepLabv3, and UNet) by 4.4%, 7.7%, and 17.6% in accuracy, respectively. Moreover, ResM-FusionNet excels in boundary detection, achieving an IoU of 0.7545, precision of 85.61%, and recall of 83.92%. These findings indicate that the proposed method not only provides robust and accurate landslide detection but also enhances segmentation performance in complex terrains.

Comparative Evaluation of State-of-the-Art Semantic Segmentation Networks for Long-Term Landslide Map Production

The production of long-term landslide maps (LAM) holds crucial importance in estimating landslide activity, vegetation disturbance, and regional stability. However, the availability of LAMs remains limited in many regions, despite the application of various machine-learning methods, deep-learning (DL) models, and ensemble strategies in landslide detection. While transfer learning is considered an effective approach to tackle this challenge, there has been limited exploration and comparison of the temporal transferability of state-of-the-art deep-learning models in the context of LAM production, leaving a significant gap in the research. In this study, an extensive series of tests was conducted to evaluate the temporal transferability of typical semantic segmentation models, specifically U-Net, U-Net 3+, and TransU-Net, using a 10-year landslide-inventory dataset located near the epicenter of the Wenchuan earthquake. The experiment results disclose the feasibility and limitations of implementing transfer-learning methods for LAM production, particularly when leveraging the power of U-Net 3+. Furthermore, following an assessment of the effects of varying data volumes, patch sizes, and time intervals, this study recommends appropriate settings for LAM production, emphasizing the balance between efficiency and production performance. The findings from this study can serve as a valuable reference for devising an efficient and reliable strategy for large-scale LAM production in landslide-prone regions.

Identification of Landslides in Mountainous Area with the Combination of SBAS-InSAR and Yolo Model

Landslides have been frequently occurring in the high mountainous areas in China and poses serious threats to peoples' lives and property, economic development, and national security. Detecting and monitoring quiescent or active landslides is important for predicting risks and mitigating losses. However, traditional ground survey methods, such as field investigation, GNSS, and total stations, are only suitable for field investigation at a specific site rather than identifying landslides over a large area, as they are expensive, time-consuming, and laborious. In this study, the feasibility of using SBAS-InSAR to detect landslides in the high mountainous areas along the Yunnan Myanmar border was tested first, with fifty-four IW mode Sentinel-1A ascending scenes from 12 January 2019 to 8 December 2020. Next, the Yolo deep-learning model with Gaofen-2 images captured on 5 December 2020 was tested. Finally, the two techniques were combined to achieve better performance, given each of them has intrinsic limitations on landslide detection. The experiment indicated that the combination could improve the match rate between detection results and references, which implied that the performance of landslide detection can be improved with the fusion of time series SAR images and optical images.

Landslide Extraction from High-Resolution Remote Sensing Imagery Using Fully Convolutional Spectral–Topographic Fusion Network

Considering the complexity of landslide hazards, their manual investigation lacks efficiency and is time-consuming, especially in high-altitude plateau areas. Therefore, extracting landslide information using remote sensing technology has great advantages. In this study, comprehensive research was carried out on the landslide features of high-resolution remote sensing images on the Mangkam dataset. Based on the idea of feature-driven classification, the landslide extraction model of a fully convolutional spectral–topographic fusion network (FSTF-Net) based on a deep convolutional neural network of multi-source data fusion is proposed, which takes into account the topographic factor (slope and aspect) and the normalized difference vegetation index (NDVI) as multi-source data input by which to train the model. In this paper, a high-resolution remote sensing image classification method based on a fully convolutional network was used to extract the landslide information, thereby realizing the accurate extraction of the landslide and surrounding ground-object information. With Mangkam County in the southeast of the Qinghai–Tibet Plateau China as the study area, the proposed method was evaluated based on the high-precision digital elevation model (DEM) generated from stereoscopic images of Resources Satellite-3 and multi-source high-resolution remote sensing image data (Beijing-2, Worldview-3, and SuperView-1). Results show that our method had a landslide detection precision of 0.85 and an overall classification accuracy of 0.89. Compared with the latest DeepLab_v3+, our model increases the landslide detection precision by 5%. Thus, the proposed FSTF-Net model has high reliability and robustness.