1. Introduction and Overview. 2. Detecting Influential Observations and Outliers. 3. Detecting and Assessing Collinearity. 4. Applications and Remedies. 5. Research Issues and Directions for Extensions. Bibliography. Author Index. Subject Index.

Regression Diagnostics: Identifying Influential Data and Sources of Collinearity

In the epicentral areas of major recent earthquakes, landslide density scales with peak ground acceleration. Topographic site effects on seismic waves are known to cause important gradients in ground acceleration in individual mountain ridges. Using landslide maps from the epicentral areas of earthquakes near Northridge, California, Chi-Chi, Taiwan, and the Finisterre Mountains of Papua New Guinea, we have investigated the control of these site effects over the location of earthquake induced slope failure. In our examples, earthquake-triggered landslides clustered near ridge crests, where the susceptibility to landsliding was greatest. This pattern is strongest in the Northridge epicentral area, and secondary landslide clusters were found in colluvial slope toes in western Taiwan and above inner gorges in the Finisterre Mountains. In contrast, rainfall-triggered landslides in the western Southern Alps of New Zealand were evenly distributed over all slope segments, and the landslide susceptibility was lowest near ridge crests. Observed patterns of earthquake induced landsliding are consistent in a diverse geological substrate. They correlate with the distribution of very steep slopes in the epicentral areas, but we demonstrate that topographic site effects can also be a strong control. Using the impedance operator method, we have modeled the propagation of seismic waves in a generic ridge-and-valley topography with and without inner gorge. This topography has little effect on incoming P waves, but a strong effect on S waves, giving rise to a significant amplification of peak ground accelerations at or near ridge crests, and at convex knickpoints within ridge flanks. The preferential orientation of landslides away from earthquake epicenters in the Finisterre Mountains and central west Taiwan is likely caused by asymmetric amplification of oblique incoming seismic waves across mountain ridges, and indicates that topographic site effects have dominated over topographic controls on landslide location in these areas. Although orientation of landslides in the Northridge area does not conform with this interpretation, our results suggest that knowledge of topographic site effects and the attenuation of seismic waves can be an important tool in the prediction of spatial patterns of earthquake induced landsliding.

Topographic site effects and the location of earthquake induced landslides

Landslide susceptibility prediction (LSP) has been widely and effectively implemented by machine learning (ML) models based on remote sensing (RS) images and Geographic Information System (GIS). However, comparisons of the applications of ML models for LSP from the perspectives of supervised machine learning (SML) and unsupervised machine learning (USML) have not been explored. Hence, this study aims to compare the LSP performance of these SML and USML models, thus further to explore the advantages and disadvantages of these ML models and to realize a more accurate and reliable LSP result. Two representative SML models (support vector machine (SVM) and CHi-squared Automatic Interaction Detection (CHAID)) and two representative USML models (K-means and Kohonen models) are respectively used to scientifically predict the landslide susceptibility indexes, and then these prediction results are discussed. Ningdu County with 446 recorded landslides obtained through field investigations is introduced as case study. A total of 12 conditioning factors are obtained through procession of Landsat TM 8 images and high-resolution aerial images, topographical and hydrological spatial analysis of Digital Elevation Modeling in GIS software, and government reports. The area value under the curve of receiver operating features (AUC) is applied for evaluating the prediction accuracy of SML models, and the frequency ratio (FR) accuracy is then introduced to compare the remarkable prediction performance differences between SML and USML models. Overall, the receiver operation curve (ROC) results show that the AUC of the SVM is 0.892 and is slightly greater than the AUC of the CHAID model (0.872). The FR accuracy results show that the SVM model has the highest accuracy for LSP (77.80%), followed by the CHAID model (74.50%), the Kohonen model (72.8%) and the K-means model (69.7%), which indicates that the SML models can reach considerably better prediction capability than the USML models. It can be concluded that selecting recorded landslides as prior knowledge to train and test the LSP models is the key reason for the higher prediction accuracy of the SML models, while the lack of a priori knowledge and target guidance is an important reason for the low LSP accuracy of the USML models. Nevertheless, the USML models can also be used to implement LSP due to their advantages of efficient modeling processes, dimensionality reduction and strong scalability.

/pdf/landslide-susceptibility-prediction-based-on-remote-sensing-tbrsqi4p05.pdf

Landslide Susceptibility Prediction Based on Remote Sensing Images and GIS: Comparisons of Supervised and Unsupervised Machine Learning Models

Landslides are one type of serious geological hazard which cause immense losses of local life and property. Landslide susceptibility prediction (LSP) can be used to determine the spatial probability of landslide occurrence in a certain area. It is important to implement LSP for landslide hazard prevention and reduction. This study developed a particle-swarm-optimized multilayer perceptron (PSO-MLP) model for LSP implementation to overcome the drawbacks of the conventional gradient descent algorithm and to determine the optimal structural parameters of MLP. Shicheng County in Jiangxi Province of China was used as the study area. In total, 369 landslides, randomly selected non-landslides, and 14 landslide-related predisposing factors were used to train and test the present PSO-MLP model and three other comparative models (an MLP-only model with the gradient descent algorithm, a back-propagation neural network (BPNN), and an information value (IV) model). The results showed that the PSO-MLP model had the most accurate prediction performance (area under the receiver operating characteristic curve (AUC) of 0.822 and frequency ratio (FR) accuracy of 0.856) compared with the MLP-only (0.791 and 0.829), BPNN (0.800 and 0.840), and IV (0.788 and 0.824) models. It can be concluded that the proposed PSO-MLP model addresses the drawbacks of the MLP-only model well and performs better than conventional artificial neural networks (ANNs) and statistical models. The spatial probability distribution law of landslide occurrence in Shicheng County was well revealed by the landslide susceptibility map produced using the PSO-MLP model. Furthermore, the present PSO-MLP model may have higher prediction and classification performances in some other fields compared with conventional ANNs and statistical models.

/pdf/landslide-susceptibility-prediction-using-particle-swarm-g85zc9dqsh.pdf

Landslide Susceptibility Prediction Using Particle-Swarm-Optimized Multilayer Perceptron: Comparisons with Multilayer-Perceptron-Only, BP Neural Network, and Information Value Models

Using the particle flow code (PFC), this work analyses the kinetic features of a landslide which occurred on May 5, 2018 in Mabian, Leshan City, Sichuan Province, China The analysis is based on geological field investigations and unmanned aerial vehicle (UAV) images The micro-strength parameters corresponding to the macroscopic characteristics of landslide rock materials are inverted by the method of the support vector machine (SVM) and PFC coupling Coupled with digital elevation model (DEM), a PFC3D numerical model of this landslide is constructed, and the slope failure process is simulated In the kinetic analysis, the landslide velocity, displacement, and energy features are taken into account The results show that the initial stage of a landslide begins with the acceleration of the overall movement, followed by the debris flow deceleration movement Its total movement duration is about 32 s, of which the main sliding time is about 16 s The maximum velocity of the landslide mass is 102 m/s, and the maximum displacement is 120 m The kinetic energy of the landslide dominates in the acceleration stage, and the collision and friction energy dissipation dominate in the deceleration phase The simulation results are in good agreement with the real landslide characteristics and the video interpretation of the landslide motion process This work could provide a new way to study related landslides as well as a theoretical reference for the quantitative risk assessment and disaster prevention and mitigation of landslides in the area

Numerical investigation of landslide kinetics for the recent Mabian landslide (Sichuan, China)

The 5 September 2018 (UTC time) Mw6.6 earthquake of Tomakomai, Japan has triggered about 10,000 landslides with high density, causing widespread concern. We attempted to establish a detailed inventory of this slope failure and use proper methods to assess landslide susceptibility in the entire affected area. To this end we applied the logistic regression (LR) and the support vector machine (SVM) for this study. Based on high-resolution (3 m) optical satellite images (planet image) before and after the earthquake, we delineated 9295 individual landslides triggered by the earthquake, occupying an area of 30.96 km2. Ten controlling factors were selected for susceptibility analysis, including elevation, slope angle, aspect, curvature, distances to faults, distances to the epicenter, Peak ground acceleration (PGA), distance to rivers, distances to roads and lithology. Using the LR and SVM, two landslide susceptibility maps were produced for the study area. The results show that in the LR model, the success rate is 84.7% between the landslide susceptibility map and the training dataset, and the prediction rate is 83.9% shown by comparing the test dataset and the landslide susceptibility map. In the SVM model, a success rate of 90.9% exists between the susceptibility map and the test samples, and a prediction rate of 87.1% from comparison of the test dataset and the landslides susceptibility map. In comparison, the performance of the SVM is slightly better than the LR model.

Planet Image-Based Inventorying and Machine Learning-Based Susceptibility Mapping for the Landslides Triggered by the 2018 Mw6.6 Tomakomai, Japan Earthquake

This paper presents the geometric and kinematic features of a landslide in Mabian, Sichuan, China, which occurred on 5 May 2018, derived from data of UAV photography. In combination with a field investigation, the UAV data permits to delineate the source area, overlap area, and accumulation area of this landslide. Coupled with DEM, its total source and accumulation volumes are estimated and the motion process is analyzed using the video record. The results show that Mabian landslide is a planar rocky downslope movement with a total horizontal projection area of 24,871 m2, source volume of 13,750 m3, accumulation volume of 213,200 m3, and the expansion rate of 55%. The sliding video demonstrates that the movement duration of the landsliding is about 16 s with a mean velocity 15.3 m/s, and the maximum velocity is 22.8 m/s. This study shows that the UAV-based aerial photography technology allow us to well characterize landslides rapidly in a quantitative manner.

Geometric and kinematic features of a landslide in Mabian Sichuan, China, derived from UAV photography

Effects of sampling intensity and non-slide/slide sample ratio on the occurrence probability of coseismic landslides

Earthquake-induced landslides (EQL) can take a heavy toll on people's life and properties, thus attracting extensive attention of the geosciences community. Carrying out earthquake-induced landslide susceptibility assessment (EQLSA) is of great significance to the prevention and reduction of such disasters as well as recovery and reconstruction in affected areas. This study examined the research status of earthquake-induced landslide susceptibility using data aspects, variable model types, and evaluation scales. To begin, we will discuss the current state and shortcomings of the earthquake landslide inventory, as well as the common landslide influencing factors that serve as the foundation for EQLSA. Then we presented the most common EQLSA methods and discussed their advantages and disadvantages. Meanwhile, we used CiteSpace to visually analyze papers in the Web of Science database with the theme word "landslide susceptibility" from 2008 to 2020. Each paper is summarized in terms of the evaluation scale. Finally, the research difficulties of landslide susceptibility in spatial scale, qualitative and quantitative problems, and spatial representation of landslide information are discussed, and future research directions are suggested. 

Earthquake-induced landslides susceptibility assessment: A review of the state-of-the-art

After a major earthquake, the rapid identification and mapping of co-seismic landslides in the whole affected area is of great significance for emergency rescue and loss assessment of seismic hazards. In recent years, researchers have achieved good results in research on a small scale and single environment characteristics of this issue. However, for the whole earthquake-affected area with large scale and complex environments, the correct rate of extracting co-seismic landslides remains low, and there is no ideal method to solve this problem. In this paper, Planet Satellite images with a spatial resolution of 3 m are used to train a seismic landslide recognition model based on the deep learning method to carry out rapid and automatic extraction of landslides triggered by the 2018 Iburi earthquake, Japan. The study area is about 671.87 km2, of which 60% is used to train the model, and the remaining 40% is used to verify the accuracy of the model. The results show that most of the co-seismic landslides can be identified by this method. In this experiment, the verification precision of the model is 0.7965 and the F1 score is 0.8288. This method can intelligently identify and map landslides triggered by earthquakes from Planet images. It has strong practicability and high accuracy. It can provide assistance for earthquake emergency rescue and rapid disaster assessment.

/pdf/automatic-extraction-of-seismic-landslides-in-large-areas-5bzxa84rqy.pdf

Automatic Extraction of Seismic Landslides in Large Areas with Complex Environments Based on Deep Learning: An Example of the 2018 Iburi Earthquake, Japan

Xiaoyi Shao

Papers

Planet Image-Based Inventorying and Machine Learning-Based Susceptibility Mapping for the Landslides Triggered by the 2018 Mw6.6 Tomakomai, Japan Earthquake

Geometric and kinematic features of a landslide in Mabian Sichuan, China, derived from UAV photography

Effects of sampling intensity and non-slide/slide sample ratio on the occurrence probability of coseismic landslides

Earthquake-induced landslides susceptibility assessment: A review of the state-of-the-art

Automatic Extraction of Seismic Landslides in Large Areas with Complex Environments Based on Deep Learning: An Example of the 2018 Iburi Earthquake, Japan