Explore the vast range of titles available.

This article offers a comprehensive AI-centric review of deep learning in exploring landslides with remote-sensing techniques, breaking new ground beyond traditional methodologies. We categorize deep learning tasks into five key frameworks—classification, detection, segmentation, sequence, and the hybrid framework—and analyze their specific applications in landslide-related tasks. Following the presented frameworks, we review state-or-art studies and provide clear insights into the powerful capability of deep learning models for landslide detection, mapping, susceptibility mapping, and displacement prediction. We then discuss current challenges and future research directions, emphasizing areas like model generalizability and advanced network architectures. Aimed at serving both newcomers and experts on remote sensing and engineering geology, this review highlights the potential of deep learning in advancing landslide risk management and preservation.

Upon the introduction of machine learning (ML) and its variants, in the form that we know today, to the landslide community, many studies have been carried out to explore the usefulness of ML in landslide research and to look at some classic landslide problems from an ML point of view. ML techniques, including deep learning methods, are becoming popular to model complex landslide problems and are starting to demonstrate promising predictive performance compared to conventional methods. Almost all the studies published in the literature in recent years belong to one of the following three broad categories: landslide detection and mapping, landslide spatial forecasting in the form of susceptibility mapping, and landslide temporal forecasting. In this paper, we present a brief overview of ML techniques, provide a general summary of the landslide studies conducted, in recent years, in the three above-mentioned categories, and make an attempt to critically evaluate the use of ML methods to model landslide processes. The paper also provides suggestions for future use of these powerful data-driven techniques in landslide studies.

Earthquake-triggered landslides frequently occur in active mountain areas, which poses great threats to the safety of human lives and public infrastructures. Fast and accurate mapping of coseismic landslides is important for earthquake disaster emergency rescue and landslide risk analysis. Machine learning methods provide automatic solutions for landslide detection, which are more efficient than manual landslide mapping. Deep learning technologies are attracting increasing interest in automatic landslide detection. CNN is one of the most widely used deep learning frameworks for landslide detection. However, in practice, the performance of the existing CNN-based landslide detection models is still far from practical application. Recently, Transformer has achieved better performance in many computer vision tasks, which provides a great opportunity for improving the accuracy of landslide detection. To fill this gap, we explore whether Transformer can outperform CNNs in the landslide detection task. Specifically, we build a new dataset for identifying coseismic landslides. The Transformer-based semantic segmentation model SegFormer is employed to identify coseismic landslides. SegFormer leverages Transformer to obtain a large receptive field, which is much larger than CNN. SegFormer introduces overlapped patch embedding to capture the interaction of adjacent image patches. SegFormer also introduces a simple MLP decoder and sequence reduction to improve its efficiency. The semantic segmentation results of SegFormer are further improved by leveraging image processing operations to distinguish different landslide instances and remove invalid holes. Extensive experiments have been conducted to compare Transformer-based model SegFormer with other popular CNN-based models, including HRNet, DeepLabV3, Attention-UNet, U2Net and FastSCNN. SegFormer improves the accuracy, mIoU, IoU and F1 score of landslide detectuin by 2.2%, 5% and 3%, respectively. SegFormer also reduces the pixel-wise classification error rate by 14%. Both quantitative evaluation and visualization results show that Transformer is capable of outperforming CNNs in landslide detection.

The rapid and accurate mapping of large-scale landslides and other mass movement disasters is crucial for prompt disaster response efforts and immediate recovery planning. As such, remote sensing information, especially from synthetic aperture radar (SAR) sensors, has significant advantages over cloud-covered optical imagery and conventional field survey campaigns. In this work, we introduced an integrated pixel-object image analysis framework for landslide recognition using SAR data. The robustness of our proposed methodology was demonstrated by mapping two different source-induced landslide events, namely, the debris flows following the torrential rainfall that fell over Hiroshima, Japan, in early July 2018 and the coseismic landslide that followed the 2018 Mw6.7 Hokkaido earthquake. For both events, only a pair of SAR images acquired before and after each disaster by the Advanced Land Observing Satellite-2 (ALOS-2) was used. Additional information, such as digital elevation model (DEM) and land cover information, was employed only to constrain the damage detected in the affected areas. We verified the accuracy of our method by comparing it with the available reference data. The detection results showed an acceptable correlation with the reference data in terms of the locations of damage. Numerical evaluations indicated that our methodology could detect landslides with an accuracy exceeding 80%. In addition, the kappa coefficients for the Hiroshima and Hokkaido events were 0.30 and 0.47, respectively.

The use of high-spatial-resolution remote sensing image technology on mobile and embedded equipment is an important and effective way for emergency rescue and evaluation decision-makers to quickly and accurately detect landslide areas. Deep learning-based landslide detection models include one-stage and two-stage models. The two-stage landslide detection models are slower. The one-stage landslide detection models are faster but less accurate. Both types of detection models have many parameters. This research aims to improve the speed, accuracy, and parameters of landslide detection models. A you only look once-small attention (YOLO-SA) landslide detection model is proposed. YOLO-SA is an improved version of the one-stage detection model YOLOv4. First, the group convolution (Gconv) and ghost bottleneck (G-bneck) residual modules are used to replace the convolution components and residual module consisting of standard convolution. The purpose is to reduce the parameters of the model. Then, on this basis, an attention mechanism is added to improve the detection accuracy of the model. Finally, the position of the attention mechanism is adjusted to determine the framework of YOLO-SA. Qiaojia and Ludian counties in Yunnan Province, China, are used as the study area to acquire three-channel (red, green, blue) historical landslide optical remote sensing images from Google Earth, with a total of 1818 images, for training the model. YOLO-SA is compared with 11 advanced models, including Faster-RCNN, 3 types of EfficientDet, 2 types of Centernet, SSD-efficient, and 4 types of YOLOv4 models. The results show that the number of YOLO-SA parameters is reduced to 1.472 mb compared to EfficientDet-D0; the accuracy is improved to 94.08% compared to Centernet-hourglass; and the speed is up to 42 f/s. In addition, the effectiveness of the YOLO-SA model for potential landslide detection is verified, with an F1 score of 90.65%.

Accurate and timely landslide mapping plays a critical role in emergency response and long-term land use planning. Deep learning–based methods represented by convolutional neural networks have been widely exploited in automatic landslide detection for their outstanding capability of feature representation and end-to-end learning mode. Most of the recent deep learning–based studies used toll-access high-resolution imagery for landslide detection. Considering demands for the future large-scale landslide mapping, this study aims to develop a new deep learning–based method to detect landslides using medium-resolution imagery and digital elevation model (DEM) data which are free-access and covered globally. Firstly, a workflow for constructing the landslide dataset is developed. Then, we design a semantic segmentation model to learn deep features and generate per-pixel landslide predictions. Specifically, the proposed network has a dual-encoder architecture with feature fusion to hierarchically represent deep features from the optical bands and DEM data. We also employ a self-attention module in the decoder of the proposed network to improve the performance. Experiments on two regions demonstrate that our method achieves the best F1 score of 79.24%, outperforming SegNet, U-Net, and Attention U-Net, the models popularly used in the semantic segmentation–based landslide detection. The proposed method may have an application potential in disaster risk assessment and post-disaster reconstruction and provide a technical reference for the large-scale landslide mapping in the future.

In response to the challenge of insufficiently labeled landslide samples, which hinders the development of supervised deep learning for landslide detection, this study presents a semi-supervised semantic segmentation model based on pixel-level contrastive learning. This method effectively uses the rich semantic and feature information in a vast pool of unlabeled samples, even when the number of labeled samples is limited, thereby achieving accurate landslide detection. In this study, we employed virtual adversarial training (VAT) to augment the model’s robustness against the most sensitive directions in the data space, effectively mitigating the insufficient model generalizability caused by the diversity in landslide morphology and surface cover. In addition, this study innovatively adopted a pixel-level contrastive learning mechanism that is constrained by probability, thereby establishing a highly structured pixel feature space. This approach facilitates the aggregation of intraclass pixels and the dispersion of interclass pixels, thus enhancing the precision and reliability of the model for detecting various types of landslides. To assess the accuracy and reliability of the model, we constructed a dataset comprising 1022 labeled samples and 2776 unlabeled samples of landslides from Planet optical imagery and digital elevation model (DEM) data within a geographical area spanning 1076.2 km in length and 254.4 km in width and ranging from western Sichuan to eastern Tibet, China. Comparative validation was conducted against existing semi-supervised methods, namely the error localization network and SemiSeg-Contrastive, as well as fully supervised approaches including SegFormer, the Swin-transformer, and Fast SCNN. The experimental results indicated that our model proficiently detected landslides, detecting 432 landslides in the study area with a detection accuracy of 0.913, an accuracy of 0.928 on the validation set, an F1 score of 0.91, and a mean intersection over union (mIoU) of 84.2%. These results surpassed those of the compared models, confirming the reliability and effectiveness of our method. The achievements of this research can serve as a reference and guide for deep-learning-based intelligent landslide detection.

Landslides are frequent all around the world, causing tremendous loss to human beings. Rapid access to the locations where landslides occur is crucial for emergency response. Most researches in landslide detection from remotely sensed images focus on small regions, which are handpicked. That makes it easy to distinguish landslides from background objects, but hard to apply in practical cases. The complicated non-landslide background pixels increase the difficulty to accurately detect landslides. In this study, we propose a technique framework to remove non-landslide background pixels for national Nepal using 12 Landsat8 images and digital elevation model (DEM). DEM is useful in removing flat areas, where landslides are less likely to occur. The framework consists of three sections: image enhancement, landslide proposal extraction, and detection model setup. Bare land, including landslides, is enhanced using vegetation index after haze/cloud re-movement. Later, calculate connective contours and propose them as potential regions that may contain landslides. For each proposal, calculate texture feature and build detection model using one of the Landsat8 images, which is further applied on other images to check its applicability and robustness. The assessment shows that the method is able to remove 99% of the background pixels in the scale of national Nepal, taking over billions of pixels. Even there is still much to do to achieve high accurate landslide detection results from large-scale images, the experiment validates a strong potential applicability for the proposed method in large-scale landslide-related analysis.

Using convolutional neural network (CNN) methods and satellite images for landslide identification and classification is a very efficient and popular task in geological hazard investigations. However, traditional CNNs have two disadvantages: (1) insufficient training images from the study area and (2) uneven distribution of the training set and validation set. In this paper, we introduced distant domain transfer learning (DDTL) methods for landslide detection and classification. We first introduce scene classification satellite imagery into the landslide detection task. In addition, in order to more effectively extract information from satellite images, we innovatively add an attention mechanism to DDTL (AM-DDTL). In this paper, the Longgang study area, a district in Shenzhen City, Guangdong Province, has only 177 samples as the landslide target domain. We examine the effect of DDTL by comparing three methods: the convolutional CNN, pretrained model and DDTL. We compare different attention mechanisms based on the DDTL. The experimental results show that the DDTL method has better detection performance than the normal CNN, and the AM-DDTL models achieve 94% classification accuracy, which is 7% higher than the conventional DDTL method. The requirements for the detection and classification of potential landslides at different disaster zones can be met by applying the AM-DDTL algorithm, which outperforms traditional CNN methods.

Damage mapping using Synthetic Aperture Radar (SAR) imagery has been studied in recent decades to support rapid response to natural disasters. Many researches have been developing coherent and incoherent change detection. However, their performances can vary depending on the types of the damages, the characteristics of the scatterers and the corresponding capability of algorithms. In particular, the coherence-based methods have been used as promising detectors over urban areas where high coherences are observed, but their detection accuracies still remain controversial over the area where low coherences are mainly observed such as the 2018 Hokkaido landslides. In order to understand the characteristics of landslide (damage) detectors for low-coherence areas and find an alternative and complementary method, we designed the coherence difference, coherence normalized difference, log-ratio, intensity correlation difference, and normalized differences of the intensity correlation assuming limited availability of dataset, and also developed multi-temporal algorithms using the coherence, intensity, and intensity correlation. They were tested and evaluated using multiple polygons extracted from aerial photos. We were able to observe that the multi-temporal intensity correlation method has the potential to detect the landslides over the low coherence region and all types of land uses.