Search

There are two technical challenges in predicting slope deformation. The first one is the random displacement, which could not be decomposed and predicted by numerically resolving the observed accumulated displacement and time series of a landslide. The second one is the dynamic evolution of a landslide, which could not be feasibly simulated simply by traditional prediction models. In this paper, a dynamic model of displacement prediction is introduced for composite landslides based on a combination of empirical mode decomposition with soft screening stop criteria (SSSC-EMD) and deep bidirectional long short-term memory (DBi-LSTM) neural network. In the proposed model, the time series analysis and SSSC-EMD are used to decompose the observed accumulated displacements of a slope into three components, viz. trend displacement, periodic displacement, and random displacement. Then, by analyzing the evolution pattern of a landslide and its key factors triggering landslides, appropriate influencing factors are selected for each displacement component, and DBi-LSTM neural network to carry out multi-data-driven dynamic prediction for each displacement component. An accumulated displacement prediction has been obtained by a summation of each component. For accuracy verification and engineering practicability of the model, field observations from two known landslides in China, the Xintan landslide and the Bazimen landslide were collected for comparison and evaluation. The case study verified that the model proposed in this paper can better characterize the "stepwise" deformation characteristics of a slope. As compared with long short-term memory (LSTM) neural network, support vector machine (SVM), and autoregressive integrated moving average (ARIMA) model, DBi-LSTM neural network has higher accuracy in predicting the periodic displacement of slope deformation, with the mean absolute percentage error reduced by 3.063%, 14.913%, and 13.960% respectively, and the root mean square error reduced by 1.951 mm, 8.954 mm and 7.790 mm respectively. Conclusively, this model not only has high prediction accuracy but also is more stable, which can provide new insight for practical landslide prevention and control engineering. [ABSTRACT FROM AUTHOR]

Landslides are dangerous disasters that are affected by many factors. Neural networks can be used to fit complex observations and predict landslide displacement. However, hyperparameters have a great impact on neural networks, and each evaluation of a hyperparameter requires the construction of a corresponding model and the evaluation of the accuracy of the hyperparameter on the test set. Thus, the evaluation of hyperparameters requires a large amount of time. In addition, not all features are positive factors for predicting landslide displacement, so it is necessary to remove useless and redundant features through feature selection. Although the accuracy of wrapper-based feature selection is higher, it also requires considerable evaluation time. Therefore, in this paper, reliability-enhanced surrogate-assisted particle swarm optimization (RESAPSO), which uses the surrogate model to reduce the number of evaluations and combines PSO with the powerful global optimization ability to simultaneously search the hyperparameters in the long short-term memory (LSTM) neural network and the feature set for predicting landslide displacement is proposed. Specifically, multiple surrogate models are utilized simultaneously, and a Bayesian evaluation strategy is designed to integrate the predictive fitness of multiple surrogate models. To mitigate the influence of an imprecise surrogate model, an intuitional fuzzy set is used to represent individual information. To balance the exploration and development of the algorithm, intuition-fuzzy multiattribute decision-making is used to select the best and most uncertain individuals from the population for updating the surrogate model. The experiments were carried out in CEC2015 and CEC2017. In the experiment, RESAPSO is compared with several well-known and recently proposed SAEAs and verified for its effectiveness and advancement in terms of accuracy, convergence speed, and stability, with the Friedman test ranking first. For the landslide displacement prediction problem, the RESAPSO-LSTM model is established, which effectively solves the feature selection and LSTM hyperparameter optimization and uses less evaluation time while improving the prediction accuracy. The experimental results show that the optimization time of RESAPSO is about one-fifth that of PSO. In the prediction of landslide displacement in the step-like stage, RESAPSO-LSTM has higher prediction accuracy than the contrast model, which can provide a more effective prediction method for the risk warning of a landslide in the severe deformation stage. [ABSTRACT FROM AUTHOR]

Geological hazards caused by strong earthquakes have caused continuous social and economic losses and destruction of the ecological environment in the hazard area, and are mostly manifested in the areas with frequent occurrence of geological hazards or the clustering of geological hazards. Considering the long-term nature of earthquakes and geological disasters in this region, this paper takes ten earthquake-stricken areas in Wenchuan earthquake zone as examples to collect shallow landslide data in 2010, combined with the spatial location of landslides and other factors. Kernel density estimation (KDE) method is used to analyze the spatial characteristics of shallow landslide. Taking the space of shallow landslide as the characteristic variable and fully considering the regulating factors of earthquake-induced landslide: terrain complexity, distance to river, distance to fault, distance to road, lithology, normalized vegetation difference index (NDVI) and ground peak acceleration (PGA) as independent variables, based on KDE and polynomial logistic regression (MLR), A quantitative model of shallow landslide in the earthquake area is constructed. The results show that: (1) PGA has the greatest impact on landslide in the study area. (2) Compared with the two-category logistic regression (two-category LR) model, the susceptibility map of landslide prediction results based on the KDE-MLR landslide susceptibility prediction model is more consistent with the actual situation. (3) The prediction accuracy of the model validation set is 70.7%, indicating that the landslide susceptibility prediction model based on KDE-MLR can effectively highlight the spatial characteristics of shallow landslides in 10 extreme disaster areas. The research results can provide decision-making basis for shallow landslide warning and post-disaster reconstruction in earthquake-stricken areas. [ABSTRACT FROM AUTHOR]

This paper discusses the role of plants in the prevention of shallow landslides induced by rain (soil slips); these phenomena, related to "hydrogeological instability," are among the most feared because their evolutionary processes can cause huge damages and losses of human lives when interacting with anthropized areas and infrastructures. The paper first highlights how the plants interact with the soil; then introduces the G-SLIP (Green – Shallow Landslides Instability Prediction) model, i.e., the simplified physically-based SLIP model, modified to predict soil slips at punctual and large scale taking into account the vegetation effects. The G-SLIP model is thus applied to a case study of the Parma Apennines (Northern Italy) by using the G-XSLIP platform. In this area, during the intense events of rain between the 4th and 5th of April 2013, numerous landslides occurred, provoking huge damages to structures and infrastructures, and consequent economic losses. The stability analyses carried out with G-XSLIP demonstrate that the presence of vegetation in the study area led to a significant reduction in the triggering of shallow landslides. Finally, an attempt at soil slip mitigation through naturalistic techniques (planting of specific vegetation) is presented. [ABSTRACT FROM AUTHOR]

The Wenchuan earthquake in 2008 induced thousands of geological hazards. Among them, earthquake-induced landslides are extremely disastrous, causing considerable social and economic losses and damage to the ecology and environment. Therefore, it is of great significance to accurately predict the spatial distribution of earthquake-induced landslides. The research in this paper focuses on ten extremely earthquake-stricken areas of the Wenchuan earthquake; landslide hazard data are collected from the study areas, and the terrain information entropy, distance to rivers, distance to faults, distance to roads, lithology, normalized difference vegetation index (NDVI), peak ground acceleration (PGA) and other landslide conditioning factors are extracted. Combined with a deep neural network (DNN), a landslide hazard spatial prediction model is constructed. Through Dataset 1 and Dataset 2, which are generated randomly, the training dataset (70%) and the validation dataset (30%) are divided to verify the robustness and accuracy of the model, and the landslide susceptibility map of the study area is obtained. Moreover, considering the area under curve (AUC), the impacts of different conditioning factors on the landslide hazard prediction model are analyzed. The research results show that the DNN-based landslide hazard spatial prediction model (AUCMean = 93.66%, RecallMean = 85.70%) has a better prediction performance in the training step. From the validation step, the influences of various factors on the spatial prediction model of landslide hazards established in this paper (from high to low) are as follows: distance to faults, lithology, distance to rivers, PGA, terrain information entropy, NDVI, and distance to roads. The landslide hazard point data and landslide susceptibility map are highly consistent, indicating that the application of a deep learning algorithm in hazard susceptibility assessment is effective and can provide a scientific basis for landslide hazard early warning and disaster prevention and mitigation in mountainous areas prone to earthquake disasters. [ABSTRACT FROM AUTHOR]

Measuring geotechnical and natural hazard engineering features, along with pattern recognition algorithms, allows us to categorize the stability of slopes into two main classes of interest: stable or at risk of collapse. The problem of slope stability can be further generalized to that of assessing landslide susceptibility. Many different methods have been applied to these problems, ranging from simple to complex, and often with a scarcity of available data. Simple classification methods are preferred for the sake of both parsimony and interpretability, as well as to avoid drawbacks such as overtraining. In this paper, an experimental comparison was carried out for three simple but powerful existing variants of the well-known nearest neighbor rule for classifying slope/landslide data. One of the variants enhances the representational capacity of the data using so-called feature line segments, while all three consider the concept of a territorial hypersphere per prototype feature point. Additionally, this experimental comparison is entirely reproducible, as Python implementations are provided for all the methods and the main simulation, and the experiments are performed using three publicly available datasets: two related to slope stability and one for landslide susceptibility. Results show that the three variants are very competitive and easily applicable. [ABSTRACT FROM AUTHOR]

Landslide damage time prediction is the most economical and reasonable means to carry out landslide control. The inverse velocity method (INVM), as the simplest and most practical method, has become the most common technique for landslide prediction nowadays. However, the application of the INVM results in false alarm when applied to step-like landslides. In this paper, we propose the conditions of using the INVM based on the trend speed ratio (TSR) to discriminate stepped landslides, analyse the real-time changes of TSR and discuss the changes of ΔTSR after the uniform deformation phase of the landslide. The results indicate that TSR reaches the extreme value one day earlier than the landslide deformation velocity; thus, TSR can help the INVM to be better applied to engineering sites and reduce the false alarm rate of risk assessment. The application of ΔTSR to eight engineering examples indicate that the new method is more sensitive and can help the traditional method to determine the starting point of landslide acceleration and the future trend of landslides. This method has better applicability and can provide new technical support for better response to landslide warning in engineering. [ABSTRACT FROM AUTHOR]

Landslide is one of the most common and severe geological disasters, which significantly endangers people's lives and properties. Therefore, adequate evaluation of landslide susceptibility is an important for disaster control and mitigation. We selected Pengyang County as the study area, and divided the indicators into different state levels by graded area ratio and landslide occurrence frequency distribution. Meanwhile, the levels of each indicator were assigned the unique scores according to the corresponding information values. Given that the issue of subjectivity in single AHP model significantly influence the model performance in landslide susceptibility prediction, a hybrid model, namely variable-weight based weighted information value (VW-AHP-IV) model, was applied in this paper for landslide susceptibility evaluation. The study area was classified into five classes by the natural breakpoint method: very high susceptibility area (8.26%), high susceptibility area (19.78%), medium susceptibility area (29.93%), low susceptibility area (31.57%) and very low susceptibility area (10.46%). In addition, this paper also discussed the influences of precipitation and human activities on landslide occurrence. According to the evaluation results and discussion, the study area was classified into three prevention and control areas: focus prevention and control area, sub-focus prevention and control area, and general prevention and control area. For each area, the corresponding prevention and control suggestions were proposed in order to reduce the occurrence of landslide disasters. [ABSTRACT FROM AUTHOR]

Logistic regression studies which assess landslide susceptibility are widely available in the literature. However, a global review of these studies to synthesise and compare the results does not exist. There are currently no guidelines for the selection of covariates to be used in logistic regression analysis, and as such, the covariates selected vary widely between studies. An inventory of significant covariates associated with landsliding produced from the full set of such studies globally would be a useful aid to the selection of covariates in future logistic regression studies. Thus, studies using logistic regression for landslide susceptibility estimation published in the literature were collated, and a database was created of the significant factors affecting the generation of landslides. The database records the paper the data were taken from, the year of publication, the approximate longitude and latitude of the study area, the trigger method (where appropriate) and the most dominant type of landslides occurring in the study area. The significant and non-significant (at the 95 % confidence level) covariates were recorded, as well as their coefficient, statistical significance and unit of measurement. The most common statistically significant covariate used in landslide logistic regression was slope, followed by aspect. The significant covariates related to landsliding varied for earthquake-induced landslides compared to rainfall-induced landslides, and between landslide type. More importantly, the full range of covariates used was identified along with their frequencies of inclusion. The analysis showed that there needs to be more clarity and consistency in the methodology for selecting covariates for logistic regression analysis and in the metrics included when presenting the results. Several recommendations for future studies were given. [ABSTRACT FROM AUTHOR]

The WHO (World Health Organization) study reports that, between 1998-2017, 4.8 million people have been affected by landslides with more than 18000 deaths. The prevailing climate change and erratic high intensity rainfall are expected to trigger more landslides, which can increase the death rates per year in future. Therefore, evolving successful mechanisms to identify and predict landslides is critical in risk reduction and post-disaster management activities. With the applications of Machine Learning , the success rates of landslide identification have been improved significantly. This review paper presents the results of data analysis on the papers published for the last three decades on varying degrees of reliability and success rate on the theme "Machine Learning for landslide identification, mitigation, and prediction". The analyses show how the reliability and accuracy of the landslide prediction model have improved considerably with the tools available in Machine Learning. Though many conventional tools such as statistical packages are available, the Machine Learning algorithms gave a robust dimension for a reliable landslide risk analysis, modeling prediction tools and post-disaster damage identification, This paper recommends a multi-modal framework for characterising landslides in all aspects using Machine Learning techniques that could outperform single modal approaches. Open research problems and future research dimensions by integrating landsat data and Machine Learning for landslide studies are also discussed in this work which would be beneficial for researchers in this field and also to the community at large across the globe. [ABSTRACT FROM AUTHOR]

This paper proposes a new, physically based, and mathematically consistent method for predicting the evolution of existing landslides and first-failure phenomena based on slope displacement measurements. The method is the latest step in a long-term research program and, as such, uses the preliminary framework introduced in two previous papers. The first characterizes slope movements through a limited number of displacement trends, and the second analyzes their dynamic characteristics. The approach is here extended to the prediction of landslide evolution and its validity and effectiveness are tested on landslides well known in the scientific literature for the accuracy of the studies carried out and, in some cases, for the consequences they have caused. Although the results obtained so far are very encouraging, in full awareness of the relevance and complexity of the subject matter, the authors emphasize that the method should be used, in the current state of knowledge, only by experienced professionals and especially for research purposes. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Landslide prediction is important for mitigating geohazards but is very challenging. There are many landslides in the Three Gorges Reservoir area, which is in the middle and upper reaches of the Yangtze River Basin in China. For the riverside landslide, the fluctuation of reservoir water level and rainfall are the main external triggering factors controlling the deformation of landslides. In this paper, the Bazimen landslide in the Three Gorges Reservoir area, which has a typical "step-like" behavior, was taken as an example, and a new method of landslide displacement prediction (VMD-FOA-SVR) was proposed. First, 9 triggering factors including the fluctuation of reservoir level and rainfall were extracted. Then, the displacement of ZG110 and triggering factors are decomposed by Variational Mode Decomposition (VMD) based on the time series analysis of landslides. Last, the trend term displacement was trained and predicted by one-dimensional cubic subsection functions, and FOA-VMD models were utilized to train and predict the periodic and random term. Results show that the prediction model established in this paper has achieved good accuracy in the total displacement of ZG110, which can effectively improve the prediction accuracy, and has high practicability and application value in the study of landslide displacement prediction. [ABSTRACT FROM AUTHOR]

Accurate early warning systems for landslides are a reliable risk-reduction strategy that may significantly reduce fatalities and economic losses. Several machine learning methods have been examined for this purpose, underlying deep learning (DL) models' remarkable prediction capabilities. The long short-term memory (LSTM) and gated recurrent unit (GRU) algorithms are the sole DL model studied in the extant comparisons. However, several other DL algorithms are suitable for time series forecasting tasks. In this paper, we assess, compare, and describe seven DL methods for forecasting future landslide displacement: multi-layer perception (MLP), LSTM, GRU, 1D convolutional neural network (1D CNN), 2xLSTM, bidirectional LSTM (bi-LSTM), and an architecture composed of 1D CNN and LSTM (Conv-LSTM). The investigation focuses on four landslides with different geographic locations, geological settings, time step dimensions, and measurement instruments. Two landslides are located in an artificial reservoir context, while the displacement of the other two is influenced just by rainfall. The results reveal that the MLP, GRU, and LSTM models can make reliable predictions in all four scenarios, while the Conv-LSTM model outperforms the others in the Baishuihe landslide, where the landslide is highly seasonal. No evident performance differences were found for landslides inside artificial reservoirs rather than outside. Furthermore, the research shows that MLP is better adapted to forecast the highest displacement peaks, while LSTM and GRU are better suited to model lower displacement peaks. We believe the findings of this research will serve as a precious aid when implementing a DL-based landslide early warning system (LEWS). [ABSTRACT FROM AUTHOR]

Compared with the study of single point motion of landslides, studying landslide block movement based on data from multiple monitoring points is of great significance for improving the accurate identification of landslide deformation. Based on the study of landslide block, this paper regarded the landslide block as a rigid body in particle swarm optimization algorithm. The monitoring data were organized to achieve the optimal state of landslide block, and the 6-degree of freedom pose of the landslide block was calculated after the regularization. Based on the characteristics of data from multiple monitoring points of landslide blocks, a prediction equation for the motion state of landslide blocks was established. By using Kalman filtering data assimilation method, the parameters of prediction equation for landslide block motion state were adjusted to achieve the optimal prediction. This paper took the Baishuihe landslide in the Three Gorges reservoir area as the research object. Based on the block segmentation of the landslide, the monitoring data of the Baishuihe landslide block were organized, 6-degree of freedom pose of block B was calculated, and the Kalman filtering data assimilation method was used to predict the landslide block movement. The research results showed that the proposed prediction method of the landslide movement state has good prediction accuracy and meets the expected goal. This paper provides a new research method and thinking angle to study the motion state of landslide block. [ABSTRACT FROM AUTHOR]

Worldwide, landslides are the most frequently occurring disaster that is very destructive and unpredictable in nature. A total of 850 landslide events were detected during 2005–2020 in the Tehri region of the Indian Himalayas. Many researchers have conducted landslide susceptibility mapping (LSM) studies for this region using different static landslide-causing factors. However, studies considering dynamic factors in predicting future landslide susceptibility scenarios are inadequate. Hence in this study, both dynamic and static factors were utilized in predicting future landslide susceptibility maps for the year 2050. The paper's main objective is the future prediction of LSM, considering future projections of land use land cover (LULC) and climate variables (precipitation and temperature). To achieve this objective, first, the geospatial database in three temporal categories, 2005–2010, 2010–2015, and 2015–2020, was prepared for the historical landslide events. Second, the landslide-causing factors were optimized and utilized in LSM for 2010, 2015, and 2020. Third, projected LULC map was generated for the year 2050 using the Artificial Neural Network-Cellular Automata (ANN-CA) model. Fourth, CMIP6 climate projection maps were prepared using the Indian Institute of Tropical Meteorology Earth system model (IITM ESM) under four shared socioeconomic pathway (SSP) scenarios. Finally, the projected maps were used as the driving parameter for the future prediction of LSM. The results reveal a high increase in the built-up area (5%) and agriculture land (4%) with a decrease in forest area (10%) in future LULC projections. The results of future LSM prediction under SSP 1–2.6, SSP 2–4.5, SSP 3–7.0, and SSP 5–8.5 climate scenarios show an increase in very high landslide susceptibility class by 2%, 4%, 7%, and 9% respectively. The predicted maps were validated utilizing the Kappa coefficient verifies the reliability of the simulated future results. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is essential for the spatial prediction of landslides and risk prevention. Physically based LSM models are confined by oversimplifications of physical processes and limited information about soil properties. Data-driven LSM models may give reliable results only when the training and the testing data have high similarity, and application in regions with different geological conditions is often inapplicable. This paper proposes four hybrid data-driven and physical models and compares these models in terms of cross-regional generalization ability and prediction uncertainty. The effects of physical module performance on the hybrid model are analyzed. For the physical modules of the four hybrid models, two-dimensional (2D) physically based models, TRIGRS and the infinite-slope stability models (ISSMs), and the three-dimensional (3D) physically based model, Scoops3D, are adopted. The data-driven modules all adopt the convolutional neural network (CNN) model. Two towns in the Three-Gorge Reservoir area of China are used as the training and testing areas. The results show that all hybrid models have better generalization ability than using the data-driven module exclusively. The prediction uncertainty is significantly reduced by pre-selecting training samples using the physical module. The optimal hybrid model is the one that integrates CNN and ISSM (under the saturated condition). It is then applied to a new region (Wushan County) to further validate the generalization ability. It can make accurate predictions without calibrating the trained model using new data from the validation area. Finally, the effectiveness of model averaging for improving the prediction performance is verified. Using model averaging, the AUC value in the validation area yields 0.834, which is even higher than the original realizations, with AUC values ranging from 0.683 to 0.817. Therefore, the optimal hybrid model can be directly used for LSM in the Three-Gorge Reservoir, and the findings can provide valuable guidance for generalization ability improvement and prediction uncertainty reduction of LSM models in other countries and regions. [ABSTRACT FROM AUTHOR]

Landslides are one of the most destructive geological disasters and have been caused many casualties and economic losses every year in the world. The reservoir area formed by the world's largest hydropower project, Three Gorges Hydropower project of China, has become a natural testing ground for landslide prediction in the hope of reducing losses. In this paper, a new algorithm with strong optimization ability, the water cycle algorithm (WCA), is combined with the extreme learning machine (ELM) to improve the prediction accuracy of step-wise landslide. The gray relational grade analysis method was adopted to determine the main influencing factors of the landslide's periodic displacement. Then, the determined factors were used as the input items of the proposed WCA-ELM model, and the corresponding periodic displacement was used as the model output item. Taking the Liujiabao landslide in the Three Gorges Reservoir area as a case history, the proposed model was verified through a comparison with the measurements. The results showed that the model has a faster convergence rate and higher prediction accuracy than the traditional back-propagation neural network model and ELM-model. The water cycle algorithm is suitable for optimizing the accuracy of the extreme learning machine model in landslide prediction. [ABSTRACT FROM AUTHOR]

In rural areas, landslides can bury houses and result in major disasters in affected areas, which can greatly hinder local economic development and construction. When landslides occur, sliding debris can result in large impact forces, causing varying degrees of damage to building structures. Given the great harm caused by landslides, this paper studies the prediction of dynamic response characteristics of building structures under the impact of the Zhengjiamo landslide. The engineering geological background of the Zhengjiamo landslide is analyzed in detail via field investigations. Then, a numerical method is presented to simulate the runout process of the sliding debris, and the runout process and final deposition area are studied. A node-to-surface contact algorithm is adopted to transfer the displacements and contact forces between the sliding debris and the building. The building structure is simulated via the finite element method (FEM). The sliding debris is simulated via the smoothed particle hydrodynamics (SPH) method. An element erosion algorithm is adopted to simulate the destruction process. The SPH-FEM fluid–structure coupling method is implemented to simulate the landslide dynamic disaster process (the impact behavior for the building). The destruction process is considered in the interactions between the sliding debris and the building on the three-dimensional terrain. The landslide motion during each stage is analyzed, including the sliding, energy dissipation, impact, and damage to the building structure. The maximum runout of the landslide is about 280 m. The maximum stress of the impact on the building is 2 × 106 Pa. The impact speed of the sliding body is generally 16.5–24.07 m/s. On the basis of this, the disaster background, disaster status, and prediction of the landslide disaster effect are studied to provide new insights into landslide disaster prevention and reduction. [ABSTRACT FROM AUTHOR]

Selecting appropriate mapping units is vital for landslide susceptibility mapping as well as pattern investigation, given that various units-based analyses extensively control the prediction performances. This paper investigated the landslide development through the interpretation and field surveys along the Yunling–Yanjing segment of the Lancang River in southeastern Tibet, and fulfil LSM with the consideration of 15 conditioning factors. Two grid unit methods (single-point and multi-point patterns) and two slope unit methods were comparatively analyzed for model training and mapping of landslide susceptibility via machine learning algorithms. The results suggest that the landslides are preferentially distributed in an elevation range of 2000–4000 m, in a slope range of 20–40°, a local relief range of 1000–2500 m, and southwest-oriented slopes. The data extracted by the multi-point method denotes a higher representation of landslide development features. All models possessed positive prediction ability for landslide susceptibility, and the multi-point method based on grid unit performed the best with the AUC exceeding 0.9. The best-performing models indicated that zones of high and very high susceptibility mainly distributed adjacent to the mainstem and some tributaries of the Lancang River. Furthermore, the distribution of "safety islands" (the slopes less prone to landslides) along National Highway G214 was reasonably illustrated as well, which provides a hazard predictability for such an important transportation corridor along the deeply-incised valley in the Lancang River. This study demonstrates a theoretical basis for the regional disaster prevention and mitigation for human activity, and provides methodological references for landslide susceptibility evaluation in similar mountainous areas over the world. [ABSTRACT FROM AUTHOR]

Slope units is an effective mapping unit for rainfall landslides prediction at regional scale. At present, slope units extracted by hydrology and morphological method report very different morphological feature and boundaries. In order to investigate the effect of morphological difference on the prediction performance, this paper presents a general landslide probability analysis model for slope units. Monte Carlo method was used to describe the spatial uncertainties of soil mechanical parameters within slope units, and random search technique was performed to obtain the minimum safety factor; transient hydrological processes simulation was used to provide key hydrological parameters required by the model, thereby achieving landslide prediction driven by quantitative precipitation estimation and forecasting data. The prediction performance of conventional slope units (CSUs) and homogeneous slope units (HSUs) were analyzed in three case studies from Fengjie County, China. The results indicate that the mean missing alarm rate of CSUs and HSUs are 31.4% and 10.6%, respectively. Receiver Operating Characteristics (ROC) analysis also reveals that HSUs is capable of improving the overall prediction performance, and may be used further for rainfall-induced landslide prediction at regional scale. [ABSTRACT FROM AUTHOR]

Landslide deformation is affected by its geological conditions and many environmental factors. So it has the characteristics of dynamic, nonlinear and unstable, which makes the prediction of landslide displacement difficult. In view of the above problems, this paper proposes a dynamic prediction model of landslide displacement based on the improvement of complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), approximate entropy (ApEn) and convolution long short-term memory (CNN-LSTM) neural network. Firstly, ICEEMDAN and ApEn are used to decompose the cumulative displacements into trend, periodic and random displacements. Then, the least square quintic polynomial function is used to fit the displacement of trend term, and the CNN-LSTM is used to predict the displacement of periodic term and random term. Finally, the displacement prediction results of trend term, periodic term and random term are superimposed to obtain the cumulative displacement prediction value. The proposed model has been verified in Bazimen landslide in the Three Gorges Reservoir area of China. The experimental results show that the model proposed in this paper can more effectively predict the displacement changes of landslides. As compared with long short-term memory (LSTM) neural network, gated recurrent unit (GRU) network model and back propagation (BP) neural network, CNN-LSTM neural network had higher prediction accuracy in predicting the periodic displacement, with the mean absolute percentage error (MAPE) reduced by 3.621%, 6.893% and 15.886% respectively, and the root mean square error (RMSE) reduced by 3.834 mm, 3.945 mm and 7.422 mm respectively. Conclusively, this model not only has high prediction accuracy but also is more stable, which can provide a new insight for practical landslide prevention and control engineering. [ABSTRACT FROM AUTHOR]

Differences in model application effectiveness, insufficient numbers of disaster samples, and unreasonable selection of non-hazard samples are common problems in landslide susceptibility studies. Therefore, in this paper, we propose a semi-integrated supervised approach to improve the prediction performance of machine learning (ML) models in landslide susceptibility studies. First, taking the lower reaches of the Jinsha River as the study area, a geospatial dataset consisting of 349 landslides, an equal number of randomly selected non-landslide points, and 12 environmental factors were randomly divided into training (70%) and testing (30%) datasets. Then, K-nearest neighbors (KNN), random forest (RF), and Bayesian-regularized neural network (BRNN) models were built. Second, the three models were combined to form an integrated weighted model. Very high- and low-prone areas were selected and, combined with the prediction results and remote sensing images, landslide and non-landslide samples were identified. The identified samples were then combined with the original samples to form new samples, which were used to sequentially construct the ensemble-supervised K-nearest neighbors (ESKNN), ensemble-supervised random forest (ESRF), and ensemble-supervised Bayesian-regularized neural network (ESBRNN) models. Finally, the area under the curve (AUC), true skill statistic (TSS), and frequency ratio (FR) values were used to test the accuracy of each model. The traditional ML model results and accuracy were improved by the semi-integrated supervised method. The ESRF model had the best prediction effect (AUC = 0.939, TSS = 0.440, and FR = 95.8%). The proposed semi-integrated supervised ML model solved the problems observed in traditional landslide susceptibility studies and provided insights for reducing variations in model applications, expanding landslide data sources, and improving non-landslide sample selection. [ABSTRACT FROM AUTHOR]

Accurate assessment of seismic landslides hazard is a prerequisite and foundation for post-disaster relief of earthquakes. An Ms 5.7 earthquake occurring on September 7, 2012, in Yiliang County, Yunnan Province, China, triggered hundreds of landslides. To explore the characteristics of coseismic landslides caused by this moderate-strong earthquake and their significance in predicting seismic landslides regionally, this study uses an artificial visual interpretation method based on a planet image with 5-m resolution to obtain the information of the coseismic landslides and establishes a coseismic landslide database containing data on 232 landslides. Nine influencing factors of landslides were selected for this study: elevation, relative elevation, slope angle, aspect, slope position, distance to river system, distance to faults, strata, and peak ground acceleration. The real probability of coseismic landslide occurrence is calculated by combining the Bayesian probability and logistic regression model. Based on the coseismic landslides, the probabilities of landslide occurrence under different peak ground acceleration are predicted using a logistic regression model. Finally, the model established in this paper is used to calculate the landslide probability of the Ludian Ms 6.5 earthquake that occurred in August 2014, 78.9 km away from the macro-epicenter of the Yiliang earthquake. The probability is verified by the real coseismic landslides of this earthquake, which confirms the reliability of the method presented in this paper. This study proves that the model established according to the seismic landslides triggered by one earthquake has a good effect on the seismic landslides hazard assessment of similar magnitude, and can provide a reference for seismic landslides prediction of moderate-strong earthquakes in this region. [ABSTRACT FROM AUTHOR]

This study determines the runout behavior (Attabad landslide, Hunza, Pakistan) of one of the biggest landslides in Pakistan's history, along the highest and strategically most important highway of the world. On January 4, 2010, at 08:36 local time, 45 Mm3 of rock mass flowed down the hill slope for 1060 m and fell in Hunza River, thus blocking the river's flow and making an artificial dam. This paper examines the landslide's failure process based on seismic data obtained from a published paper. The average velocity of the slide was found to be 14.32 m/s. To better understand the landslide dynamics and failure phenomena, a numerical simulation was conducted using DAN3D to simulate displaced materials' runout behavior. Simulation results indicate that the slope's failure lasted for 70 s, which is in good agreement with seismic wave recordings of 70 s. The combined frictional–Voellmy model obtained the most accurate results for simulation. Further, to verify the results, another simulation was run using RAMMS debris flow software; it was found that the results of both the software's are in good agreement. It is expected that the selected model and its parameters will help understand similar kind of rock avalanches in the area, which will help concerned agencies improve landslide prediction along Karakoram Highway. [ABSTRACT FROM AUTHOR]

Rainfall-induced landslides are currently one of the most frequent disasters in China. Compared with rainfall, the increase of soil moisture and its continuous infiltration of soil are the direct factors leading to landslides. However, few researches have studied landslide forecasting taking the soil moisture into consideration. In addition, soil moisture data have an important depth attribute. Soil moisture in root zone is difficult to obtain, and the separate comparison of the impact of the root zone and shallow soil moisture on landslide is more scarce. After comparing the commonly used satellite data, this article chose the CLDAS-V2.0 data set as the source of soil moisture with the depths of 0–10 cm and 100–200 cm. One hundred and sixty-six rainfall-induced landslides that occurred in Tongzi and Xishui counties from February to July 2020 were studied. This paper first obtains the effective rainfall that has the strongest correlation with the landslide and then uses the effective rainfall to explore the best combination of rainfall and soil moisture, including separate modeling and joint modeling of rainfall and soil moisture. Then support vector machine, logistic regression and three decision tree models are developed to predict the landslides. The results show that the combined model of rainfall and soil moisture is better than the model that only considers rainfall or soil moisture, and the landslide forecasting accuracy is improved by more than 5%, which is about 30% higher than the traditional ED rainfall threshold method. Landslide prediction model is proposed to be used as a help for urban planning and government decision-making. [ABSTRACT FROM AUTHOR]

On October 2017, due to continuous rainfall, there was a massive river blockage induced by a landslide in Guang'an Village, Chongqing, China. Long-term monitoring analysis has shown that there remain four strong deformation areas on the slope, which seriously threaten the life and property of nearby residents. In this paper, a granular flow model and an elasto-visco-plasticity model were applied to reproduce and predict the landslide event that hit Guang'an Village. The results showed that the landslide gradually moved along the sliding surface, pushing loose deposits and blocking the Xixi River. The numerical reproduction results of the 2017 event are consistent with the actual slope deformation and failure process and deposit morphology. The simulated maximum depth-averaged velocity of this landslide was approximately 1.89 m/s, and the height of the landslide dam was approximately 10 m. After the landslide occurred in 2017, several large deformation areas appeared in the vicinity of the sliding area, and the right rear side of the sliding mass in area III has the largest deformation volume, accompanied by the most developed surface crack and the most intense deformation. There is a risk that the Xixi river will be blocked again. Therefore, with the same parameter and numerical model, a sliding–pushing–blocking dynamic prediction analysis of the strong deformation area III was conducted. The pushing motion of the mass in this area will reactivate the landslide mass observed in 2017. The maximum depth-averaged velocity of deformation area III was 0.5 m/s, and the maximum depth-averaged velocity of landslide deposition was 0.45 m/s. The length of the blocking dam formed by the mass of deformation area III along river was approximately 780 m, 30 m longer than that in 2017. The predicted height of the landslide dam was 14.5 m, approximately 4.5 m higher than that in 2017. The length of the landslide dam reservoir was predicted to be 2.55 km along the Xixi River, which may submerge the Waping Village. This study supports the landslide hazard prevention, reveals the whole movement process of sliding-pushing-blocking, and provides a new research idea and method for the landslide movement prediction. Hence, this study can serve as a reference for the hazard prevention and mitigation of such chain disasters. [ABSTRACT FROM AUTHOR]

The topic of rainfall thresholds for landslide occurrence was thoroughly investigated, producing abundance of case studies at different scales of analysis and several technical and scientific advances. We reviewed the most recent papers published in scientific journals, highlighting significant advances and critical issues. We collected and grouped all the information on rainfall thresholds into four categories: publication details, geographical distribution and uses, dataset features, threshold definition. In each category, we selected descriptive information to characterize each one of the 115 rainfall threshold published in the last 9 years. The main improvements that stood out from the review are the definition of standard procedures for the identification of rainfall events and for the objective definition of the thresholds. Numerous advances were achieved in the cataloguing of landslides too, which can be defined as one of the most important variables, together with rainfall data, for drawing reliable thresholds. Another focal point of the reviewed articles was the increased definition of thresholds with different exceedance probabilities to be employed for the definition of warning levels in landslide early warning systems. Nevertheless, drawbacks and criticisms can be identified in most part of the recent literature on rainfall thresholds. The main issues concern the validation process, which is seldom carried out, and the very frequent lack of explanations for the rain gauge selection procedure. The paper may be used as a guide to find adequate literature on the most used or the most advanced approaches followed in every step of the procedure for defining reliable rainfall thresholds. Therefore, it constitutes a guideline for future studies and applications, in particular in early warning systems. The paper also aims at addressing the gaps that need to be filled to further enhance the quality of the research products in this field. The contribution of this manuscript could be seen not only as a review of the state of the art, but also an effective method to disseminate the best practices among scientists and stakeholders involved in landslide hazard management. [ABSTRACT FROM AUTHOR]

Machine learning models have been widely used in landslide susceptibility prediction. However, landslide multidimensional feature extraction, model generalization ability, and prediction quantification of deep learning are still challenging. This paper proposes a new approach, the landslide density-based bidirectional long short-term memory (LD-BiLSTM) model with multichannel input and an optimized sampling strategy to predict and map landslide susceptibility in active seismic mountainous areas of Sichuan Province, China. First, to ensure the generalization ability of the LD-BiLSTM model, other regions in Sichuan were selected as the model training area independent of the prediction area (Luding County). Multichannel landslide datasets were constructed to extract high-dimensional geospatial features of landslides. Subsequently, the landslide density of each grid cell was utilized as the label for the corresponding input sample. The LD-BiLSTM model was improved by using transfer learning and sampling optimization strategies, which makes our method attenuate the impact of historical landslide inventory deviation on the spatial susceptibility mode compared with the existing DL model, which usually uses landslide objects (LO) as input sample labels. Model performance evaluation results show that the LD-BiLSTM model (precision = 0.903, recall = 0.899, F1-score = 0.901, Area under receiver operating characteristic curve (AUC) = 0.940) outperformed the LO-BiLSTM model (precision = 0.812, recall = 0.815. F1-score = 0.813, AUC = 0.910) in the case areas. Meanwhile, the performance of the LD-BiLSTM model (AUC = 0.9407) significantly outperformed both the information value (IV) (AUC = 0.7207) model and the random forest (RF) (AUC = 0.8116) models in the landslide prediction area (Luding), which confirms that the proposed LD-based method is superior to traditional LO-based methods. Significantly, our approach can effectively extract the spatial distribution of landslides and predict potential landslides in complex high-mountain environments. [ABSTRACT FROM AUTHOR]

Rainfall and change in reservoir water levels often lead to landslides, threatening the lives and properties of people in neighboring areas. Therefore, it is necessary to predict the landslide displacement. This paper proposes a novel coupling method of extreme gradient boosting (XGBoost) and Hodrick–Prescott (HP) filtering method to predict the landslide displacement. First, the HP filtering method is used to decompose the total landslide displacement into trend displacement and periodic displacement. The trend displacement is affected by the potential energy of landslide and the boundary constraints, and it is predicted by using the least square polynomial function. Rainfall and reservoir water level fluctuation are the main factors affecting the periodic displacement, and the extreme gradient boosting is used to predict the periodic displacement. The total displacement is obtained by adding the predicted trend displacement and the predicted periodic displacement. The Bazimen and Baishuihe landslides are taken as an example to verify the ability of this proposed model. Compared with other prediction methods (back propagation neural network (BP-NN), support vector machine regression (SVR)), this proposed method has the higher accuracy. Therefore, the proposed method can effectively predict the displacement of landslides. [ABSTRACT FROM AUTHOR]

For landslide displacement, interval predictions are generally more realistic and reliable compared with traditional point predictions. This paper presents a new interval prediction method for landslide displacement integrating dual-output least squares support vector machine (DO-LSSVM) and particle swarm optimization (PSO) algorithms. In this new method, the PSO algorithm is employed to optimize coefficients of the least squares support vector machine (LSSVM) model for obtaining point prediction results, and the interval prediction of the landslide displacement is made based on the dual-outputs obtained from the DO-LSSVM model. To assess the rationality of the predictions, three performance evaluation indicators, including the prediction interval coverage probability (PICP), normalized mean prediction interval width (NMPIW), and coverage width-based criterion (CWC), are established. Case studies of the Tanjiahe landslide and the Baishuihe landslide in the Three Gorges Reservoir region are then used to demonstrate the effectiveness of the proposed method in predicting the landslide displacement interval. The case study results demonstrate that this new method has the best overall performance compared with other existing methods, and this new method can provide accurate and reliable results for the medium- to long-term interval prediction of landslide displacement. [ABSTRACT FROM AUTHOR]

The Fifth World Landslide Forum (WLF5) was postponed from 2-6 November 2020 to 2-6 November 2021 due to COVID-19. Full color books Six volumes of full color books titled I Understanding and Reducing Landslide Disaster Risk i which are the inaugural volumes of the new ICL book series "ICL contribution to landslide disaster risk reduction" (ISSN 2662-1894 (print version) and e-ISSN 2662-1908 (electronic version)) will be published in January 2021. The six volumes of books include all accepted papers submitted to WLF5. [Extracted from the article]

Landslide events cause significant financial losses, human casualties, and irreversible changes in the natural landscape. In this paper, we have addressed the mapping of landslides zones using the extracted Cartosat-1 Digital Elevation Model (DEM) and a knowledge-based numerical rating system. The main objective of the study is to use the Weight of Evidence (WoE) technique to produce a Landslide Hazards Zonation (LHZ) map and a Landslide Susceptible Map (LSM) to establish a relationship between landslide causality factors and past landslide locations. For the prediction and generation of the LSM, accurate DEM is extracted using the noise-free stereo images of the Cartosat-1 sensor. This research proposed a prediction model for landslide susceptibility mapping based on the combination of a knowledge-based numerical rating system, remote sensing, and the WoE technique. The WoE technique and information value method are used to calculate the weightage and ranking of each landslide causality factor. The sum of the landslide causality factor products calculates the Landslide Susceptible Index (LSI) value for every pixel. The area under concern was classified into five susceptibility classes based on the derived LSI, ranging from very low to scars. The overall prediction and forecast accuracy of the LSM generated using the WoE technique is 92.68%. [ABSTRACT FROM AUTHOR]

Long-runout landslides can be extremely hazardous and unpredictable. The prediction of long-runout landslides is challenging because it is unclear what factors control their mobility, and it is unclear how to best measure their runout given that they traverse changing topography. In this paper, we document the development and statistical evaluation of a Landslide Runout Score (LRS) system to predict short, medium, and long runout using a new mobility measure, the unitless Runout Number L/A1/2 (where L is landslide length and A is landslide area). The Runout Number has previously been correlated to three geomorphological factors (planimetric curvature, sand content, and upslope contributing area normalized to landslide area), so the LRS uses these factors as inputs. These factors are readily calculated using geographic information systems (GIS) and publicly available data sources. The LRS system predicts runout categories (short, medium, and long) with one-vs.-all accuracies (i.e., percentage of correct predictions within a given class) of 75, 58, and 72%, respectively, for a total weighted accuracy of approximately 65%. The results of this work are summarized in a worksheet that can be used by geologists and engineers to develop preliminary predictions of landslide runout behavior, which can be incorporated into or used alongside regional-scale landslide hazard assessments. [ABSTRACT FROM AUTHOR]

Landslide displacement prediction is a challenging and important subject in landslide research. To improve the prediction accuracy of and reduce disasters caused by landslides, we propose a selective ensemble deep bidirectional Random Vector Functional Link Network (sedb-RVFLN) for landslide displacement prediction in which each independent hidden layer is linked to a different output layer. In this paper, to reduce the number of hidden nodes without affecting the efficiency of network training, an incremental learning method is utilized to make some hidden nodes not randomly chosen. Moreover, we apply selected partial hidden layers instead of all hidden layers to construct a selective ensemble. The ensemble method adopted by sedb-RVFLN does not require training multiple independent networks, and the entire sedb-RVFLN only needs to be trained once. Finally, we conduct extensive experiments on real landslide datasets from the Huangdeng Hydropower Station in China to demonstrate the effectiveness of our model. [ABSTRACT FROM AUTHOR]

Numerous large-scale fragmented bedrock landslides developed along major fault system is a world-wide phenomenon, which are often characterized with repeated reactivation throughout histories. Due to the large-scale and deep-seated features, it is normally difficult to control such landslides, which in turn pose great threat to local residents and infrastructures. Therefore, monitoring and forecasting these gigantic landslides has become a key protocol for risk reduction. This paper introduces such a typical massive landslide, named Yahuokou landslide, besides Min River in Zhouqu County, Gansu Province, China. Reactivated on July 16, 2019 with a volume of approximately 4×106m3, moving slowly and transitionally starting from top part, its toe had partially blocked the Min River and destroyed roads and houses eventually by August 11, 2019. As to emergency response for such huge slow-moving landslide, there is no standard national protocols. Therefore, how to make effective emergency decision has become a challenge. Based on previous experiences, integrated multi-methods, including UAV imagery interpretation, we applied GNSS monitoring and field investigations in the early stages of landsliding, in order to assist the decision-making. The results show that the movement path of the current displacement is consistent with that of the 1989 reactivation event, and the slide body was separated into three relatively independent blocks with different sliding velocities and responses to rainfall. The upper and lower blocks appeared less affected by rainfall, while the middle block responded more to the changes in precipitations. It proves that the combined approaches using a variety of monitoring techniques can play an effective role in the monitoring of rapidly deformed transitional large-scale landslides, and can also provide a set of reference methods for the emergency disposal of similar landslide hazards. [ABSTRACT FROM AUTHOR]

Slope stability management systems (SSMSs) have been developed by multiple state transportation agencies to assess landslides adjacent to highways and aide in the effective allocation of resources for slope and/or roadway repairs. SSMSs catalog and analyze slope failures through the use of three main components: a landslide data collection system, a geographic information systems (GIS) database, and a hazard prioritization system. The components form a landslide management system used for the identification or prediction of landslide risk areas and the determination of landslide hazards to motorists. The Alabama Department of Transportation (ALDOT) has not previously employed a SSMS, which limits the ability of ALDOT engineers and geologists to effectively manage landslide hazards along highways. This paper discusses the development of a landslide collection system and database developed to improve the ability of ALDOT to identify common causes and locations of slope failures along Alabama highways. The collected data were converted into a GIS database, which allows for correlations between landslides and additional spatial data, such as average precipitation and surface geology. This paper presents a brief review of similar SMSSs, reviews the proposed database, and discusses preliminary observations. The data collected from this study can be used to identify common causes of landslides along Alabama highways and select efficient remediation options. [ABSTRACT FROM AUTHOR]

The assessment of earthquake-induced landslide hazards is an important prerequisite for disaster prevention and reduction in tectonic active areas. However, few studies have considered the amplification effect of site and topography on ground motion parameters and made the peak ground acceleration (PGA) correction. Based on Newmark's method, taking Litang County, Sichuan Province, China, as the study area, considering the site amplification effect and topographic amplification effect, this paper carried out the assessment of landslide hazards under the action of occasional earthquakes with an exceedance probability of 10% and rare earthquakes with an exceedance probability of 2%. The results show that the hazard of earthquake-induced landslides is higher in the high slopes of loose rock in the middle of Litang County and the steep rock slopes with large topographic relief in the northeast, and low in the southern plateau and central basins. The site and topographic conditions have a significant effect on the nonlinear amplification of PGA, and the corrected PGA is even magnified by 2–3 times in steep mountains. Compared with the occasional earthquakes, the influence of rare earthquakes on the initiation and movement distance of landslides is remarkably improved. This study can provide a valuable reference for potential earthquake-induced landslide hazard assessment and seismic landslide emergency response in Litang County. [ABSTRACT FROM AUTHOR]

Prediction model plays an important role in the early warning of reservoir landslides. This paper proposes a novel synthetic prediction model, the Bayesian optimized random forest-combined Kalman filter (BORF-KF) in which the Kalman filter and random forest algorithm are used to predict the trend and periodic displacements of the cumulative landslide displacement, respectively. To improve the accuracy of the model, the Bayesian algorithm is used to optimize the parameters, and periodic changes of rainfall and reservoir water level are considered. The applicability, efficiency, and accuracy of the proposed prediction model is successfully verified against monitoring time series obtained from the Outang landslide, a giant resurrected ancient landslide in the Three Gorges reservoir of China. The results show the ground deformation of the reservoir landslide exhibits notable step-like characteristics, which has strong correlation with the concentrated rainfall and the decrease of the reservoir water level. Moreover, predicted cumulative displacement error is less than 2%, suggesting the BORF-KF model attains a high prediction accuracy and can be applied to the prediction of reservoir landslides with abrupt step-like sections. [ABSTRACT FROM AUTHOR]

In many geotechnical applications, especially in the study of weather-induced landslides, a reliable soil hydraulic characterization in unsaturated conditions is required. Currently, the experimental techniques that neglect the hydraulic hysteresis represent the greatest limitation to landslide forecasting. In this paper, a procedure to obtain an unsaturated soil hydraulic characterization on natural pyroclastic samples is proposed and verified. The approach enables the evaluation of the soil hydraulic properties along the main drying path and wetting/drying cycles to fully quantify the effects of the hydraulic hysteresis. Pyroclastic soil samples collected at a test site at Mount Faito in the Campania region (southern Italy) were tested. The experimental investigation consisted of a sequence of testing phases: a constant-head hydraulic conductivity test, a forced evaporation test followed by several wetting–drying cycles, and a drying test in a pressure plate apparatus. The hysteretic model proposed by Parker and Lenhard (1987) was adopted to fit the data, while inverse modelling of the forced evaporation tests allowed to derive the model parameters. Therefore, the main drying and wetting branches and the soil response to drying and wetting cycles from any reversal point were reproduced with the model, which suitably described the hysteretic behaviour of the pyroclastic soil under all conditions and along all paths. [ABSTRACT FROM AUTHOR]

Information about the long-term spatiotemporal evolution of landslides can improve our understanding of the landslide development process and can help prevent landslide disasters. This paper describes the Xiaozhuang landslide triggered by a historical earthquake and rainfall in Tianshui, Northwest China. The landslide is dominated by rotational-sliding movement. Several new failures and many fissures formed in the landslide area as a result of the 2013 Ms 6.6 Minxian earthquake and rainfall. Accordingly, field investigations, borehole drilling, geotechnical laboratory tests, and numerical calculations were conducted to study the mechanism of the landslide and to forecast its stability. A triaxial creep test of the slip soil indicates that the axial deformation of the mudstone increases with increasing water content. Numerical simulations suggest that failure is prone to occur within the deep part of the landslide under earthquake conditions. If the input seismic acceleration exceeds 0.2 g, the landslide will become unstable. Furthermore, the horizontal peak ground acceleration near the surface of the landslide is greater than that at depth. During a strong earthquake, the unstable regions are primarily located in the middle of the landslide and at its crest. When the rainfall intensity rate is 200 mm/d, the factor of safety is 1.319 and a dangerous zone appears in the lower and middle parts of the landslide. [ABSTRACT FROM AUTHOR]

This paper presents a geomechanical model test for analyzing rainfall-induced slope instability. The proposed method integrates HCA726S tilt sensors, micro soil pressure sensors, pore water pressure sensors, three-dimensional laser scanners, and other instruments to monitor tilt angle, stress, vertical displacement, and morphology of the slope. The tilting deformation and stress response were analyzed, and the landslide evolution process is summarized. Based on the tilt deformation curves obtained from the tilt sensors, it can be concluded that shallow landslide exhibits creep characteristics, and the creep behavior can be divided into three stages: primary, secondary, and tertiary creep. A linear relationship between the reciprocal tilting rate and time was observed during the primary and tertiary creep stages, and a linear equation was established. A reciprocal tilting rate of 0 min/° was then input into the linear equation to obtain the time of initial and complete slope failure. The predicted landslide failure times were consistent with the actual recorded times obtained from the model tests. Thus, tilt deformation is a significant early warning indicator or slope instability and could be used to predict landslides for disaster prevention and mitigation. [ABSTRACT FROM AUTHOR]

Mapping susceptibility of landslide disaster is essential in subtropical area, where abundant rainfall may trigger landslide and mudflow, causing damages to human society. The purpose of this paper is to propose an integrated methodology to achieve such a mapping work with improved prediction results using hybrid modeling taking Chongren, Jiangxi as an example. The methodology is composed of the optimal discretization of the continuous geo-environmental factors based on entropy, weight of evidence (WoE) calculation and application of the known machine learning (ML) models, e.g., Random Forest (RF), Support Vector Machine (SVM) and Logistic Regression (LR). The results show the effectiveness of the proposed hybrid modeling for landslide hazard mapping in which the prediction accuracy vs the validation set reach 82.35–91.02% with an AUC [area under the receiver operating characteristic (ROC) curve] of 0.912–0.970. The RF algorithm performs best among the observed three ML algorithms and WoE-based RF modeling will be recommended for the similar landslide risk prediction elsewhere. We believe that our research can provide an operational reference for predicting the landslide hazard in the subtropical area and serve for disaster reduction and prevention action of the local governments. [ABSTRACT FROM AUTHOR]

The monitoring data of landslide deformation are characterized by non-smooth, nonlinear and random changes, and the cumulative changes of the monitored objects have both monotonous growth trends and short-term fluctuations. The GM(1,1) model can get better results only when the data series are monotonous. Due to the limitations of the model, the prediction accuracy of the GM(1,1) model is limited to a certain extent. An improved algorithm based on the GM(1,1) model and the empirical mode decomposition (EMD-GM(1,1) model) for deformation prediction was presented to improve the forecast accuracy in this paper. Firstly, EMD was used to effectively separate the nonlinear high-frequency and low-frequency components hidden in the deformation sequence; then the moving average method was applied to build a prediction model for high-frequency component, and the GM(1,1) was applied to build the prediction model for low-frequency one according to the characteristics of each component; finally, the predicted value of each component was superimposed. The experimental results indicate that the optimized EMD-GM(1,1) model combines the advantages of the two models to separate effectively the different frequency components of the deformation sequence, which has higher prediction accuracy. Compared with the conventional GM(1,1) model, DGM(2,1) model and the Linear fitting model, the proposed model could satisfactorily describe the landslide deformation prediction practically. [ABSTRACT FROM AUTHOR]

Based on the machine learning algorithms, prediction models for landslide displacement with step-like behavior in the reservoir area were established for landslides prevention and reduction; these models could predict a given test set very well. However, due to the length and the sequence of the training set in prediction models, the predictive ability of these prediction models could not be evaluated accurately if just validated with a given test set. To solve the problem, a hybrid reliability model was proposed. Complimentary ensemble empirical mode decomposition (CEEMD) algorithm was used to decompose the accumulated displacement into the trend displacement and the periodic displacement firstly. The Gauss function was used to predict the trend displacement, and the random forest (RF) and back propagation neural network (BPNN) algorithms were employed to predict the periodic displacement. Furthermore, a novel performance function for the reliability analysis of the displacement prediction model was derived to address failure probabilities in different cases. The Baijiabao landslide in the Three Gorges Reservoir Area was taken as an example for reliability analysis of the prediction model for landslide displacement with step-like behavior, and the predictive ability of the CEEMD-RF model and the CEEMD-BPNN model were compared. The results indicated that the CEEMD-RF model and CEEMD-BPNN model both can accurately predict the accumulated displacement of the given test set; the predictive value obtained with the CEEMD-RF model or the CEEMD-BPNN model showed uncertainties of the prediction model for landslide displacement and the predictive ability of the CEEMD-RF model was more reliable than the CEEMD-BPNN model under different cases. The failure probability proposed in the paper could evaluate the predictive ability of the model more accurately and comprehensively compared with the existing assessment indices. [ABSTRACT FROM AUTHOR]

In the machine learning models, it is desirable to remove most redundant features from the data set to reduce the data processing time and to improve accuracy of the models. In this paper, chi-square (CS) and backward elimination (BE), which are well-known feature selection methods, were used for the optimum selection of input features/factors for training artificial neural network (ANN) for landslide susceptibility modeling. Initially, seventeen landslide affecting factors were considered for the ANN model which were reduced to twelve and eleven based on the ANN optimized by CS (CSANN) and BE (BEANN), respectively. Accuracy (ACC), Kappa Index, root mean square error (RMSE), and area under the receiver operating characteristic (AUROC) curve were used to evaluate and validate performance of the models. Results show that both the feature selection methods (CS and BE) improved significantly performance of the hybrid BEANN and CSANN models in comparison to single ANN model. Results indicated that performance of the BEANN model (AUROC 0.963; ACC 91.31) is the best in comparison to CSANN (AUROC 0.950; ACC 89.80) and ANN (AUROC 0.949; ACC 76.40) models in the accurate prediction of landslide susceptible areas/zones. Therefore, it is reasonable to state that the BE is more effective feature selection method than the CS in improving performance of the ANN model and thus, it can be used for better landslide susceptibility analysis for the landslide management of the area. [ABSTRACT FROM AUTHOR]

An accurate landslide displacement prediction is an important part of landslide warning system. Aiming at the dynamic characteristics of landslide evolution and the shortcomings of traditional static prediction models, this paper proposes a dynamic prediction model of landslide displacement based on singular spectrum analysis (SSA) and stack long short-term memory (SLSTM) network. The SSA is used to decompose the landslide accumulated displacement time series data into trend term and periodic term displacement subsequences. A cubic polynomial function is used to predict the trend term displacement subsequence, and the SLSTM neural network is used to predict the periodic term displacement subsequence. At the same time, the Bayesian optimization algorithm is used to determine that the SLSTM network input sequence length is 12 and the number of hidden layer nodes is 18. The SLSTM network is updated by adding predicted values to the training set to achieve dynamic displacement prediction. Finally, the accumulated landslide displacement is obtained by superimposing the predicted value of each displacement subsequence. The proposed model was verified on the Xintan landslide in Hubei Province, China. The results show that when predicting the displacement of the periodic term, the SLSTM network has higher prediction accuracy than the support vector machine (SVM) and auto regressive integrated moving average (ARIMA). The mean relative error (MRE) is reduced by 4.099% and 3.548% respectively, while the root mean square error (RMSE) is reduced by 5.830 mm and 3.854 mm respectively. It is concluded that the SLSTM network model can better simulate the dynamic characteristics of landslides. [ABSTRACT FROM AUTHOR]

Prediction of landslide movement is an efficient approach in the reduction in landslide risk. However, it is also a tough task due to the scientific challenges in forecasting a sophisticated natural disaster. This paper proposes a VMD-MIC-M-KELM (variational mode decomposition-maximum information coefficient-multi-kernel extreme learning machine) technique for prediction of landslide movements. The original displacement is first decomposed into a predefined number of components by VMD. Then, the triggers of each component are selected based on MIC between subseries and influencing factors. The decomposed terms are predicted by M-KELM respectively via k-fold cross-validation. Finally, predicted total displacement is achieved by summing up all forecasting subseries. A case study of Miaodian landslide (China) is presented for validation of the developed model. The verification results demonstrate the higher ability of the approach to forecast monthly displacement for periods up to 12 months as compared to the Poly-KELM and SVR models. Thus, improved monthly predictions may be achieved with constantly updated datasets from the monitoring system, which would offer reliable information for early warning of landslide. [ABSTRACT FROM AUTHOR]

Early Warning Systems (EWS) are efficient tools for preventing and mitigating the risks associated to landslides occurrence. In this paper, an integrated methodology for landslides' analysis is presented and described. Such methodology is aimed at the creation of early warning systems and is based on the integration between a modern monitoring technique, such as the Ground-Based Interferometric Synthetic Aperture Radar (GBInSAR), along with advanced numerical modelling. The paper also shows the application of the proposed methodology to the case study of a rockslide in central Italy. The integration between monitoring data, thanks to a GBInSAR survey and advanced numerical simulations with the combined Finite-Discrete Elements Method (FDEM), allowed for the definition of a set of surface velocity thresholds to be adopted for the long-term monitoring of the landslide and for the creation of an effective EWS. [ABSTRACT FROM AUTHOR]