Landslide Samples Research Articles

Impacts of bridge constructions on channel dynamics and sediment aggradation: An integrated discussion, West Bengal, India

Channel dynamics, including channel migration, erosion, and deposition, is a significant geomorphological phenomenon. It has been noted that the Gish River exists with its widest extension between 1913 and 2021, causing a bottleneck situation. The section G4 (Gish-4) experienced the most significant squeezing character over time. The catchment landslide-induced sediments, mostly transported in the monsoon by 1st and 2nd order streams, deposited at the beds near the rail and road bridges of the rivers Lish, Gish, and Chel. Landslide susceptibility mapping (LSM) and sediment transport index (STI) maps specify the zones of sediment generation and aggradation. Results of low ‘b” value 0.77 + /−0.04 specify active tectonics and instability of the area. A petrographic analysis of landslide samples and river bed sediments justifies that the landslide connected streams are continuously transported and deposited in the river bed. In the Himalayan foothill rivers like Lish, Gish, and Chel, channel planform dynamics may be the result of landslide occurrences, that induce huge sediments in the rivers and sediment transport index indicates the deposition of the sediments near rail and road bridges in spatio-temporal scale.

Uncertainties in landslide susceptibility prediction modeling: A review on the incompleteness of landslide inventory and its influence rules

Landslide inventory is an indispensable output variable of landslide susceptibility prediction (LSP) modelling. However, the influence of landslide inventory incompleteness on LSP and the transfer rules of LSP resulting error in the model have not been explored. Adopting Xunwu County, China, as an example, the existing landslide inventory is first obtained and assumed to contain all landslide inventory samples under ideal conditions, after which different landslide inventory sample missing conditions are simulated by random sampling. It includes the condition that the landslide inventory samples in the whole study area are missing randomly at the proportions of 10%, 20%, 30%, 40% and 50%, as well as the condition that the landslide inventory samples in the south of Xunwu County are missing in aggregation. Then, five machine learning models, namely, Random Forest (RF), and Support Vector Machine (SVM), are used to perform LSP. Finally, the LSP results are evaluated to analyze the LSP uncertainties under various conditions. In addition, this study introduces various interpretability methods of machine learning model to explore the changes in the decision basis of the RF model under various conditions. Results show that (1) randomly missing landslide inventory samples at certain proportions (10%–50%) may affect the LSP results for local areas. (2) Aggregation of missing landslide inventory samples may cause significant biases in LSP, particularly in areas where samples are missing. (3) When 50% of landslide samples are missing (either randomly or aggregated), the changes in the decision basis of the RF model are mainly manifested in two aspects: first, the importance ranking of environmental factors slightly differs; second, in regard to LSP modelling in the same test grid unit, the weights of individual model factors may drastically vary.

An Accurate Recognition Method for Landslides Based on a Semi-Supervised Generative Adversarial Network: A Case Study in Lanzhou City

With the development of computer technology, landslide recognition based on machine learning methods has been widely applied in geological disaster management and research. However, in landslide identification, the problems of an insufficient number of samples and an imbalance of samples are often ignored; that is, landslide samples are much smaller than non-landslide samples. In order to solve this problem, taking the main urban area of Lanzhou City as an example, this paper proposes to construct a semi-supervised generated countermeasure network (SSGAN) model, which aims to achieve high performance with a limited number of labeled samples for precise landslide identification, and to help prevent and reduce the harm caused by disasters. In order to express the environmental characteristics of landslide development and the optical texture features of landslide occurrence, the study constructs three sets of samples to represent landslide features, including a landslide influencing factor sample set, a Sentinel-2A optical remote sensing sample set, a joint influencing factor and Sentinel-2A sample set. The three kinds of sample sets are transferred to SSGAN for training to form a comparative study. The results show that the joint sample set has excellent feature results in discriminator and generator. Through the experimental comparison, the model proposed in this paper is compared with the model without semi-supervised generated confrontation training. The experimental results show that the proposed method is better than the unsupervised adversarial learning model in terms of accuracy, F1 score, Kappa coefficient, and MIoU. A total of 160 landslides have been identified in the study area, with a total area of 10.328 km2, with an accuracy rate of 83%. Therefore, the generated results are accurate and reliable, and show that SSGAN can better distinguish landslides from non-landslides in an image, under the condition of obtaining a large number of unmarked environmental features; enhance the effect of landslide classification in complex geographical environment; and then put forward effective suggestions for the prevention and control of landslides and geological disasters in the main urban area of Lanzhou.

A landslide susceptibility assessment method considering the similarity of geographic environments based on graph neural network

Landslide susceptibility assessment (LSA) is vital for landslide mitigation and management. Existing LSA methods only consider local environmental characteristics associated with landslides, while neglecting the characteristics of remote yet interconnected geographic environments. In addition, the datasets for landslide samples do not consider the equilibrium among various geographic environmental characteristics. Ultimately, the landslide susceptibility mapping (LSM) generated is unreliable. We propose an LSA method based on the similarity of geographic environments and the equilibrium of landslide samples. We selected the Bailong River Basin (BRB) as the study area. Our proposed LSA method has four steps: (1) We constructed slope units using the curvature watershed method (CWM) based on the digital elevation model (DEM) to generate geographic nodes and selected 12 landslide influencing factors (LIFs) through multicollinearity analysis to extract geographic node features. (2) We constructed an association graph of geographic environment similarity constraints based on geographic node features using the cosine similarity method to correlate landslide and geographical environments. (3) We constructed sample datasets for an equal number of landslide and non-landslides based on various geographic environments. (4) We constructed a graph neural network (GNN) model based on the association graph to predict the susceptibility of unknown geographic nodes, obtaining a reliable LSM. Compared with random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) models, our proposed model framework outperforms in the LSA. The area under the receiver operating characteristic curve (AUC) values improved by 6.2%, 5.7%, and 1.8%, respectively. Specifically, our model can predict landslides across space in areas with few samples. Our proposed model offers an effective approach and essential technical support for landslide disaster investigation and prevention.

Landslide susceptibility assessment using deep learning considering unbalanced samples distribution

Landslide susceptibility assessment (LSA) is fundamental for managing landslide geological disasters. This study presents a deep learning approach (DNN-MSFM) designed to enhance LSA modeling, particularly addressing limitations caused by the unbalanced distribution of data samples in applied datasets. DNN-MSFM approach combines a deep neural network (DNN) and a mean squared false misclassification loss function (MSFM) to handle unbalanced samples from the algorithmic perspective. The model's performance was evaluated on an unbalanced dataset containing mapping units' records of 293 landslide samples and 653 non-landslide samples from the Baota District, China. Its effectiveness was assessed through statistical metrics and compared against DNN and Support Vector Machine (SVM) basic models. The results demonstrated a significant performance enhancement from the DNN-MSFM (OverallAccuracy = 0.889 and area under the receiver operating characteristic curve (AUC) = 0.84), indicating its effectiveness in learning the underlying landslide susceptibility features and demonstrating its ability to provide improved predictions even in areas with unbalanced landslide samples. Moreover, the study emphasizes the importance of considering balanced loss functions in training DNN under various imbalance degrees and contributes to expanding the applicability of DNN in LSA modeling. Also, this study builds a foundation for further enhancements of deep learning methods for geological disaster assessments.

Landslide susceptibility assessment based on frequency ratio and semi-supervised heterogeneous ensemble learning model.

Epistemic uncertainty in data-driven landslide susceptibility assessment often tends to be increased by the limited accuracy of an individual model, as well as uncertainties associated with the selection of non-landslide samples. To address these issues, this paper centers on the landslide disaster in Ji'an City, China, and proposes a heterogeneous ensemble learning method incorporating frequency ratio (FR) and semi-supervised sample expansion. Based on the superimposed results of 12 environmental factor frequency ratios (FFR), non-landslide samples were selected and input into light gradient boosting machine (LightGBM), random forest (RF), and convolutional neural network (CNN) models for prediction along with historical landslide samples. The predicted probability values are integrated by four heterogeneous ensemble strategies to expand samples from high-confidence results. The model's performance is evaluated using the area under the receiver operating characteristic curve (AUC), partition frequency ratio (PFR), and other verification methods. The results demonstrate that the negative sample based on FFR sampling is more accurate than the random sampling method, and the FR-SSELR model based on frequency ratio sampling and semi-supervised ensemble strategy exhibits the highest performance (AUC = 0.971, ACC = 0.941). A more reasonable landslide susceptibility map was drawn based on this model, with the lowest percentage of landslides in the low and very low susceptibility zones (sum of PFR = 0.194), as well as the highest percentage of landslides in the high and very high susceptibility zones (sum of PFR = 6.800). Furthermore, the FR-SSELR model improved economic benefits by 3.82-14.2%, offering valuable guidance for decision-making regarding landslide management and the sustainability of Ji'an City.

Refined landslide susceptibility mapping in township area using ensemble machine learning method under dataset replenishment strategy

Landslide susceptibility mapping (LSM) warrants considerable attention as a prerequisite for risk assessment and prevention in response to the increasing global occurrences of landslides. However, refined LSM at the township scale still faces the problem of the limited number of landslides and the oversight of relevant factors associated with different landslide types. This work is dedicated to propose a novel dataset replenishment strategy designed to address landslide sample scarcity, and to identify dominant factors in high landslide susceptibility zones to refine LSM at township scale for decision makers. Herein, the Wuling County in the Three Gorges Reservoir area of China was taken as taken as the research case. Initially, field investigation and calibration of 21 landslides yielded accumulation and rock areas, and the corresponding impact factors were therefore proposed to construct input features for machine learning facilitated by factor diagnosis using Pearson correlation coefficient (PCC) and multicollinearity test. Subsequently, a training and validation dataset split of 8: 2 was randomly generated, enabling the application of ensemble machine learning model for LSM prediction. The study culminated in the feasibility of dataset replenishment strategy, which was employed to explore uncertainties and identify governing factors in LSM. The results indicate that the bagging-ANN model exhibits superior performance in both accumulation and rock areas, with Areas Under Curve (AUC) of 0.987 and 0.994. Furthermore, the dataset replenishment strategy emerges as instrumental in enhancing the reliability of LSM, as evidenced by an 8.97 % reduction in average value (AVG) and a 11.00 % increase in standard deviation (STD). The governing factors for landslides in accumulation and rock areas are designated as river erosion and height, respectively. Together with the excellent performance, this study is expected to provide a promising reference for LSM in other townships worldwide.

Landslide susceptibility prediction modelling based on semi‐supervised XGBoost model

In the process of landslide susceptibility prediction (LSP) modelling, there are some problems in the model dataset relating to landslide and non‐landslide samples, such as landslide sample errors, subjective randomness and low accuracy of non‐landslide sample selection. In order to solve the above problems, a semi‐supervised machine learning model for LSP is innovatively proposed. Firstly, Yanchang County of Shanxi Province, China, is taken as the study area. Secondly, the frequency ratio values of 12 environmental factors (elevation, slope, aspect, etc.) and the randomly selected twice non‐landslides are used to form the initial model datasets. Thirdly, an extreme gradient boosting (XGBoost) model is adopted for training and testing the initial datasets, so as to produce initial landslide susceptibility maps (LSMs) which are divided into very low, low, moderate, high and very high susceptibility levels. Next, the landslide samples in initial LSMs with very low and low susceptibility levels are excluded to improve the accuracy of landslide samples, and the unlabelled twice non‐landslide samples in initial LSMs with low and very low susceptibility levels are randomly selected to ensure the accuracy of non‐landslide samples. These new obtained landslide and non‐landslide samples are reimported into XGBoost model to construct the semi‐supervised XGBoost (SSXGBoost) model. Finally, accuracy, kappa coefficient and statistical indexes of susceptibility indexes are adopted to assess the LSP performance of XGBoost and SSXGBoost models. Results show that SSXGBoost model has remarkably better LSP performance than that of XGBoost model. Conclusively, the proposed SSXGBoost model effectively overcomes the problems that the accuracy of landslide samples needs to be further improved and that non‐landslide samples are difficult to select accurately.

A novel landslide susceptibility prediction framework based on contrastive loss

ABSTRACT Recently, the positive unlabeled (PU) learning algorithms have proven highly effective in generating accurate landslide susceptibility maps. The algorithms categorize samples exclusively into positive samples (landslides) and unlabeled samples for training, eliminating random or subjective selection of non-landslide samples. However, existing PU learning algorithms face limitations in capturing correct negative samples in multi-genesis landslide areas, leading to lower prediction accuracy. To address this issue, the PU-pullbaggingDT algorithm was proposed in this study. This integrated method combines the strengths of two techniques: the superior ranking performance of the PU-baggingDT algorithm and the low bias of the contrastive learning approach. The contrastive learning introduces a new contrastive loss of PU learning (PUpull loss), which pulls the distance of similar landslide samples in the projection space closer based on the validation accuracy threshold, without the need for data augmentation and class probability. The PUpull loss relaxes the tightness toward unlabeled samples, reducing the impact of incorrectly defined non-landslide samples on prediction results in multi-genesis landslide areas. The proposed algorithm outperforms existing PU-learning and machine learning methods (support vector machine, decision tree, logistic regression, AdaBoost, and XGBoost) with random selection of negative samples for predicting landslide susceptibility in China’s Zigui County, as demonstrated by comprehensive evaluation metrics. The landslide susceptibility mapping utilizes equal interval division and ranking, achieving approximately a 90% landslide percentage in areas with very high and high susceptibility in Zigui County. This demonstrates the capability of the proposed algorithm to effectively predict landslide susceptibility in complex geological settings.

A novel deep learning framework for landslide susceptibility assessment using improved deep belief networks with the intelligent optimization algorithm

This research proposed a novel deep learning framework that combines the Laplace function sparse regularized continuous deep belief network (LSCDBN) and the Gray Wolf Optimization Algorithm (GWO) and the Whale Optimization Algorithm (WOA), to perform landslide susceptibility assessment. This framework mitigates the challenges of feature homogenization for continuous input variables for landslide condition factors, limited landslide samples, and local optima in the training process. To facilitate this investigation, a meticulous compilation of existing landslide occurrences was used to create a database comprising 18 landslide conditioning factors. To compare the performance of the model, a set of statistical indicators was employed. The results demonstrate the superior performance of both the LSCDBN-GWO model (AUC = 0.952, RMSE = 0.182) and LSCDBN-WOA model (AUC = 0.964, RMSE = 0.174) when compared to the alone LSCDBN model (AUC = 0.913, RMSE = 0.291). It is noteworthy that the performance of the LSCDBN model outperformed that of lone machine learning models (SVM, BP, RF, and LR), lone deep learning models (RNN and CNN), and hybrid deep learning models (CNN-GWO and CNN-WOA). Therefore, it is evident that the proposed LSCDBN-WOA framework can generate models that are optimally suited for landslide susceptibility assessment.

Machine Learning for Landslide Susceptibility Mapping Using Phyton in Sigi Biromaru Area (Near Palu), Central Sulawesi, Indonesia

Sigi Biromaru is near Palu City; both experienced the Palu earthquake on 28 September 2018. Unlike Palu City, a flat area, Sigi Biromaru is hilly, so it experienced landslides after the big earthquake. This study performed landslide susceptibility mapping for Sigi Biromaru using a machine learning method, namely random forest. Nine parameters were used, i.e., altitude, slope, lithology, peak ground acceleration, land cover, river density, lineament density, rainfall, and aspect. The total data points were 530, half landslide samples and the other half non-landslide samples. We used 70% of the data points to train the model and the rest to evaluate the model. The landslide susceptibility map produced by random forest with no hyperparameter tuning has an area under the curve (AUC) of 0.94 for the success rate and 0.91 for the predictive rate. This study used a novel method in which the non-landslide locations represent the safe zone area, sampled randomly from the lowest class of landslide susceptibility area based on a bivariate statistical model. This study is highly recommended for the initial phase of landslide hazard mitigation.

A Comparative Study of Landslide Susceptibility Mapping Using Bagging PU Learning in Class-Prior Probability Shift Datasets

Landslide susceptibility mapping is typically based on binary prediction probabilities. However, non-landslide samples in modeling datasets are often unlabeled data, and the phenomenon of class-priori shift, that is, the proportion of landslide samples frequently deviates from real-world scenarios and is spatially heterogeneous. By comparing the classification performance and predicted probability distributions across multiple unbalanced datasets with known and unknown sample proportions, this study assesses the landslide susceptibility model’s generalization ability in the context of class-prior shifts. The study investigates the potential of Bagging PU Learning, a semi-supervised learning approach, in improving the generalization performance of landslide susceptibility models and proposes the Bagging PU-GDBT algorithm. Our findings highlight the effectiveness of Bagging PU Learning in enhancing the recall of landslides and the generalization capabilities of models on unbalanced datasets. This method reduces prediction uncertainties, especially in high and very high susceptibility zones. Furthermore, results emphasize the superiority of models trained on balanced datasets with 1:1 sample ratio for landslide susceptibility mapping over those trained on unbalanced datasets.

Landslide Susceptibility Prediction Using Machine Learning Methods: A Case Study of Landslides in the Yinghu Lake Basin in Shaanxi

Landslide susceptibility prediction (LSP) is the basis for risk management and plays an important role in social sustainability. However, the modeling process of LSP is constrained by various factors. This paper approaches the effect of landslide data integrity, machine-learning (ML) models, and non-landslide sample-selection methods on the accuracy of LSP, taking the Yinghu Lake Basin in Ankang City, Shaanxi Province, as an example. First, previous landslide inventory (totaling 46) and updated landslide inventory (totaling 46 + 176) were established through data collection, remote-sensing interpretation, and field investigation. With the slope unit as the mapping unit, twelve conditioning factors, including elevation, slope, aspect, topographic relief, elevation variation coefficient, slope structure, lithology, normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), distance to road, distance to river, and rainfall were selected. Next, the initial landslide susceptibility mapping (LSM) was obtained using the K-means algorithm, and non-landslide samples were determined using two methods: random selection and semi-supervised machine learning (SSML). Finally, the random forest (RF) and artificial neural network (ANN) machine-learning methods were used for modeling. The research results showed the following: (1) The performance of supervised machine learning (SML) (RF, ANN) is generally superior to unsupervised machine learning (USML) (K-means). Specifically, RF in the SML model has the best prediction performance, followed by ANN. (2) The selection method of non-landslide samples has a significant impact on LSP, and the accuracy of the SSML-based non-landslide selection method is controlled by the ratio of the number of landslide samples to the number of mapping units. (3) The quantity of landslides has an impact on how reliably the results of LSM are obtained because fewer landslides result in a smaller sample size for LSM, which deviates from reality. Although the results in this dataset are satisfactory, the zoning results cannot reliably anticipate the recently added landslide data discovered by the interpretation of remote-sensing data and field research. We propose that the landslide inventory can be increased by remote sensing in order to achieve accurate and impartial LSM since the LSM of adequate landslide samples is more reasonable. The research results of this paper will provide a reference basis for uncertain analysis of LSP and regional landslide risk management.

Landslide susceptibility assessment in multiple urban slope settings with a landslide inventory augmented by InSAR techniques

Landslide susceptibility assessment (LSA) evaluates the likelihood of landslide occurrences and can help mitigate and prevent landslide risks. Recently, there have been vast applications of data-driven LSA methods owing to the increased availability of high-quality satellite data and landslide inventories. However, two issues remain to be addressed, as follows: (a) Items in a landslide inventory are mainly historical landslides from the interpretation of optical images and site investigation, resulting in predictive models trained with these items being insensitive to undetectable slope movements, such as slow-moving landslides that have not yet occurred; (b) Most study areas contain a variety of landslide-prone geographical settings that a single model can not accommodate well. Considering the complex landslide causes in Hong Kong with a land area of approximately 1108 km2, we proposed the utilization of multi-temporal InSAR techniques to generate weak landslide samples from slopes with ground surface movements for landslide inventory augmentation; and meta-learn intermediate representations for the fast adaptation of LSA models corresponding to different landslide-prone geographical settings. Besides, we performed feature permutation to identify dominant landslide-predisposing factors. The LSA results in Hong Kong revealed that slope deformation in several mountainous areas is closely associated with the occurrence of recorded landslides. By augmenting the landslide inventory using InSAR techniques, the proposed method enhanced the LSA models' capacity to identify slow-moving landslides and achieved better statistical performance. The discussion highlights that slope and stream power index (SPI) are the key landslide-predisposing factors in Hong Kong, but the dominant landslide-predisposing factors will vary under different geographical conditions. By comparison with the methods that treat LSA as a binary classification problem, such as support vector machine, multilayer perceptron, deep belief network, and random forest based LSA methods, the proposed method entails a fast-learning strategy and outperforms these methods in data-driven model evaluation indicators, e.g., by 3–6% in accuracy, 2–6% in precision, 1–2% in recall, 3–5% in F1-score, and approximately 10% in Cohen Kappa. The information about the relative importance of landslide predisposing factors, derived through feature permutation, can foster guidance for targeted landslide prevention schemes, such as constructing and maintaining slope consolidation facilities in areas where slope is the dominant landslide-predisposing factor.

Investigation of Landslide Susceptibility Decision Mechanisms in Different Ensemble-Based Machine Learning Models with Various Types of Factor Data

Machine learning (ML)-based methods of landslide susceptibility assessment primarily focus on two dimensions: accuracy and complexity. The complexity is not only influenced by specific model frameworks but also by the type and complexity of the modeling data. Therefore, considering the impact of factor data types on the model’s decision-making mechanism holds significant importance in assessing regional landslide characteristics and conducting landslide risk warnings given the achievement of good predictive performance for landslide susceptibility using excellent ML methods. The decision-making mechanism of landslide susceptibility models coupled with different types of factor data in machine learning methods was explained in this study by utilizing the Shapley Additive exPlanations (SHAP) method. Furthermore, a comparative analysis was carried out to examine the differential effects of diverse data types for identical factors on model predictions. The study area selected was Cenxi, Guangxi, where a geographic spatial database was constructed by combining 23 landslide conditioning factors with 214 landslide samples from the region. Initially, the factors were standardized using five conditional probability models, frequency ratio (FR), information value (IV), certainty factor (CF), evidential belief function (EBF), and weights of evidence (WOE), based on the spatial arrangement of landslides. This led to the formation of six types of factor databases using the initial data. Subsequently, two ensemble-based ML methods, random forest (RF) and XGBoost, were utilized to build models for predicting landslide susceptibility. Various evaluation metrics were employed to compare the predictive capabilities of different models and determined the optimal model. Simultaneously, the analysis was conducted using the interpretable SHAP method for intrinsic decision-making mechanisms of different ensemble-based ML models, with a specific focus on explaining and comparing the differential impacts of different types of factor data on prediction results. The results of the study illustrated that the XGBoost-CF model constructed with CF values of factors not only exhibited the best predictive accuracy and stability but also yielded more reasonable results for landslide susceptibility zoning, and was thus identified as the optimal model. The global interpretation results revealed that slope was the most crucial factor influencing landslides, and its interaction with other factors in the study area collectively contributed to landslide occurrences. The differences in the internal decision-making mechanisms of models based on different data types for the same factors primarily manifested in the extent of influence on prediction results and the dependency of factors, providing an explanation for the performance of standardized data in ML models and the reasons behind the higher predictive performance of coupled models based on conditional probability models and ML methods. Through comprehensive analysis of the local interpretation results from different models analyzing the same sample with different sample characteristics, the reasons for model prediction errors can be summarized, thereby providing a reference framework for constructing more accurate and rational landslide susceptibility models and facilitating landslide warning and management.

SE-YOLOv7 Landslide Detection Algorithm Based on Attention Mechanism and Improved Loss Function

With the continuous development of computer vision technology, more and more landslide identification detection tasks have started to shift from manual visual interpretation to automatic computer identification, and automatic landslide detection methods based on remote sensing satellite images and deep learning have been gradually developed. However, most existing algorithms often have the problem of low precision and weak generalization in landslide detection. Based on the Google Earth Engine platform, this study selected landslide image data from 24 study areas in China and established the DN landslide sample dataset, which contains a total of 1440 landslide samples. The original YOLOv7 algorithm model was improved and optimized by applying the SE squeezed attention mechanism and VariFocal loss function to construct the SE-YOLOv7 model to realize the automatic detection of landslides in remote sensing images. The experimental results show that the mAP, Precision value, Recall value, and F1-Score of the improved SE-YOLOv7 model for landslide identification are 91.15%, 93.35%, 94.54%, and 93.94%, respectively. At the same time, through a field investigation and verification study in Qianyang County, Baoji City, Shaanxi Province, comparing the detection results of SE-YOLOv7, it is concluded that the improved SE-YOLOv7 can locate the landslide location more accurately, detect the landslide range more accurately, and have fewer missed detections. The research results show that the algorithm model has strong detection accuracy for many types of landslide image data, which provides a technical reference for future research on landslide detection based on remote sensing images.

Landslide risk of regional roads: Consider the road mileage of expected losses

Considering the road disruption caused by landslides, this study develops a quantitative method to evaluate the landslide risk encountered by regional roads. First, a logistic regression model was performed to evaluate the landslide possibility with nine landslide factors and 359 landslide samples. Subsequently, network self-adjustment and three vulnerable factors were integrated to depict road vulnerability. After determining the cost of different road sections, the landslide risk of roads was calculated and expressed as a potentially expected loss. Results show that the study area highlights the road segments with low landslide risk, focusing on the expected loss of 0.0–0.1 million CNY; while lines of Tahe-Great Khingan-Mohe and Mohe-Huma maintain the highest risk, and the expected loss exceeds 0.8 million CNY. Furthermore, the lower the road class, not only the greater the expected loss, but the higher the road mileage exposed to landslides, which facilitates the mitigation strategy for different types of roads in response to landslides.

DSFA: cross-scene domain style and feature adaptation for landslide detection from high spatial resolution images

ABSTRACT Rapid and accurate landslide inventory mapping is significant for emergency rescue and post-disaster reconstruction. Nowadays, deep learning methods exhibit excellent performance in supervised landslide detection. However, due to differences between cross-scene images, the performance of existing methods is significantly degraded when directly applied to another scene, which limits the application of rapid landslide inventory mapping. In this study, we propose a novel Domain Style and Feature Adaptation (DSFA) method for cross-scene landslide detection from high spatial resolution images, which can leverage labeled source domain images and unlabeled target domain images to mine robust landslide representations for different scenes. Specifically, we mitigate the large discrepancy between domains at the dataset level and feature level. At the dataset level, we introduce a domain style adaptation strategy to shift landslide styles, which not only bridges the domain gap, but also increases the diversity of landslide samples. At the feature level, adversarial learning and domain distance minimization are integrated to narrow large feature distribution discrepancies for learning domain-invariant information. In addition, to avoid information omission, we improve the U-Net3+ model. Extensive experimental results demonstrate that DSFA has superior detection capability and outperforms other methods, showing its great application potential in unsupervised landslide domain detection.

Landslide Recognition from Multi-Feature Remote Sensing Data Based on Improved Transformers

Efficient and accurate landslide recognition is crucial for disaster prevention and post-disaster rescue efforts. However, compared to machine learning, deep learning approaches currently face challenges such as long model runtimes and inefficiency. To tackle these challenges, we proposed a novel knowledge distillation network based on Swin-Transformer (Distilled Swin-Transformer, DST) for landslide recognition. We created a new landslide sample database and combined nine landslide influencing factors (LIFs) with remote sensing images (RSIs) to evaluate the performance of DST. Our approach was tested in Zigui County, Hubei Province, China, and our quantitative evaluation showed that the combined RSIs with LIFs improved the performance of the landslide recognition model. Specifically, our model achieved an Overall Accuracy (OA), Precision, Recall, F1-Score (F1), and Kappa that were 0.8381%, 0.6988%, 0.9334%, 0.8301%, and 0.0125 higher, respectively, than when using only RSIs. Compared with the results of other neural networks, namely ResNet50, Swin-Transformer, and DeiT, our proposed deep learning model achieves the best OA (98.1717%), Precision (98.1672%), Recall (98.1667%), F1 (98.1615%), and Kappa (0.9766). DST has the lowest number of FLOPs, which is crucial for improving computational efficiency, especially in landslide recognition applications after geological disasters. Our model requires only 2.83 GFLOPs, which is the lowest among the four models and is 1.8242 GFLOPs, 1.741 GFLOPs, and 2.0284 GFLOPs less than ResNet, Swin, and DeiT, respectively. The proposed method has good applicability in rapid recognition scenarios after geological disasters.

Geo‐environment‐aware adversarial transfer learning method for landslide susceptibility evaluation of complex mountainous areas

AbstractLandslide susceptibility evaluation (LSE) is a critical issue for disaster prevention. Limited by labor cost and observation technology, landslide samples are extremely limited in dense vegetation‐covered and remote areas, making the common supervised learning model underfit with limited samples. Therefore, the reliability of analysis results in mountainous areas is low. Transfer learning can achieve reliable assessment without the need for representative samples. However, transfer learning suffers from environmental heterogeneity in regional LSE and may transfer incorrect classification knowledge of landslide features from dissimilar environments. Aiming at these challenges, we proposed a geo‐environment‐aware LSE method based on unsupervised adversarial transfer learning. The key is to consider the difference in landslide features in different geo‐environments. The study areas were first divided into multiple sub‐environments, and the similarity between the sub‐environments was calculated. Then an environment‐aware adversarial transfer model was built for fine‐grained aligning of the landslide feature with similar sub‐environments and for reducing negative transfer between dissimilar environments. The fitted classification model was employed to predict the target regions and to generate the final LSE. The experimental results indicated that the proposed method achieves reliable LSE for sample‐free regions. The accuracy of the proposed method is 7–12% better than commonly used methods such as support vector machines, random forests, and artificial neural networks. The performance of the proposed method is even close to the results of supervised learning with the presence of representative samples, and it also performs more globally and objectively in susceptibility mapping. These results reveal that the proposed method effectively transfers the knowledge of landslide susceptibility from other regions to the sample‐free region.