Spatiotemporal modelling of rainfall-induced landslides using machine learning

Landslides - Natural terrain landslides are mainly triggered by rainstorms in Hong Kong, which pose great threats to life and property. To mitigate landslide risk, building a prediction model which...     

Comparison of machine learning models for gully erosion susceptibility mapping

Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3% of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.     

An optimization on machine learning algorithms for mapping snow avalanche susceptibility

Natural Hazards - Mapping avalanche-prone areas to mitigate damages is important and vital for safety and development planning. New hybrid models are introduced for snow avalanche susceptibility...     

A multi-method approach to study the stability of natural slopes and landslide susceptibility mapping

In this paper, a multi-method approach for the assessment of the stability of natural slopes and landslide hazard mapping applied to the Dakar coastal region is presented. This approach is based on the effective combination of geotechnical field and laboratory works, of GIS, and of mechanical (deterministic and numerical) stability analysis. By using this approach, valuable results were gained regarding instability factors, landslide kinematics, simulation of slope failure and coastal erosion. This led to a thorough assessment and strong reduction in the subjectivity of the slope stability and hazard assessment and to the development of an objective landslide danger map of the SW coast of Dakar. Analysis of the results shows that the slides were influenced by the geotechnical properties of the soil, the weathering, the hydrogeological situation, and the erosion by waves. The landslide susceptibility assessment based on this methodological approach has allowed for an appropriate and adequate consideration of the multiple factors affecting the stability and the optimization of planning and investment for land development in the city.     

Mapping susceptibility of rainfall-triggered shallow landslides using a probabilistic approach

To prepare a landslide susceptibility map is essential to identify hazardous regions, construct appropriate mitigation facilities, and plan emergency measures for a region prone to landslides triggered by rainfall. The conventional mapping methods require much information about past landslides records and contributing terrace and rainfall. They also rely heavily on the quantity and quality of accessible information and subjectively of the map builder. This paper contributes to a systematic and quantitative assessment of mapping landslide hazards over a region. Geographical Information System is implemented to retrieve relevant parameters from data layers, including the spatial distribution of transient fluid pressures, which is estimated using the TRIGRS program. The factor of safety of each pixel in the study region is calculated analytically. Monte Carlo simulation of random variables is conducted to process the estimation of fluid pressure and factor of safety for multiple times. The failure probability of each pixel is thus estimated. These procedures of mapping landslide potential are demonstrated in a case history. The analysis results reveal a positive correlation between landslide probability and accumulated rainfall. This approach gives simulation results compared to field records. The location and size of actual landslide are well predicted. An explanation for some of the inconsistencies is also provided to emphasize the importance of site information on the accuracy of mapping results.     

A heuristic approach to global landslide susceptibility mapping

Landslides can have significant and pervasive impacts to life and property around the world. Several attempts have been made to predict the geographic distribution of landslide activity at continental and global scales. These efforts shared common traits such as resolution, modeling approach, and explanatory variables. The lessons learned from prior research have been applied to build a new global susceptibility map from existing and previously unavailable data. Data on slope, faults, geology, forest loss, and road networks were combined using a heuristic fuzzy approach. The map was evaluated with a Global Landslide Catalog developed at the National Aeronautics and Space Administration, as well as several local landslide inventories. Comparisons to similar susceptibility maps suggest that the subjective methods commonly used at this scale are, for the most part, reproducible. However, comparisons of landslide susceptibility across spatial scales must take into account the susceptibility of the local subset relative to the larger study area. The new global landslide susceptibility map is intended for use in disaster planning, situational awareness, and for incorporation into global decision support systems.     

Landslide susceptibility assessment using SVM machine learning algorithm

This paper introduces the current machine learning approach to solving spatial modeling problems in the domain of landslide susceptibility assessment. The latter is introduced as a classification problem, having multiple (geological, morphological, environmental etc.) attributes and one referent landslide inventory map from which to devise the classification rules. Three different machine learning algorithms were compared: Support Vector Machines, Decision Trees and Logistic Regression. A specific area of the Fruška Gora Mountain (Serbia) was selected to perform the entire modeling procedure, from attribute and referent data preparation/processing, through the classifiers' implementation to the evaluation, carried out in terms of the model's performance and agreement with the referent data. The experiments showed that Support Vector Machines outperformed the other proposed methods, and hence this algorithm was selected as the model of choice to be compared with a common knowledge-driven method – the Analytical Hierarchy Process – to create a landslide susceptibility map of the relevant area. The SVM classifier outperformed the AHP approach in all evaluation metrics (κ index, area under ROC curve and false positive rate in stable ground class).     

A subjective and objective integrated weighting method for landslides susceptibility mapping based on GIS

The purpose of this study is to present a weighting method, integrating subjective weight with objective weight, for landslides susceptibility mapping based on geographical information system (GIS). First, the landslide inventory, aspect, slope, proximity to streams of drainage network, proximity to railway, proximity to road, topography, elevation, lithology, tectonic activity and annual precipitation, including their subclasses, were taken as independent landslide causal factors. Second, objective weights of the causal factors were calculated according to the landslide area density based on entropy weighting method, and key factors were selected according to the rank of the objective weights. Third, trapezoidal fuzzy number weighting approach was used to assess the sub-classes of each key factor. Finally, a case study was carried out in Guizhou province, China. A landslide susceptibility map was created using weighted linear combination model based on GIS. Using a predicted map of probability, the study area was classified into four categories of landslide susceptibility: low, moderate, moderate-high, and high.     

Flood susceptibility modelling using advanced ensemble machine learning models

Floods are one of nature's most destructive disasters because of the immense damage to land, buildings, and human fatalities.It is difficult to forecast the areas that are vulnerable to flash flooding due to the dynamic and complex nature of the flash floods.Therefore, earlier identification of flash flood susceptible sites can be performed using advanced machine learning models for managing flood disasters.In this study, we applied and assessed two new hybrid ensemble models, namely Dagging and Random Subspace(RS) coupled with Artificial Neural Network(ANN), Random Forest(RF), and Support Vector Machine(SVM) which are the other three state-of-the-art machine learning models for modelling flood susceptibility maps at the Teesta River basin, the northern region of Bangladesh.The application of these models includes twelve flood influencing factors with 413 current and former flooding points, which were transferred in a GIS environment.The information gain ratio, the multicollinearity diagnostics tests were employed to determine the association between the occurrences and flood influential factors.For the validation and the comparison of these models, for the ability to predict the statistical appraisal measures such as Freidman, Wilcoxon signed-rank, and t-paired tests and Receiver Operating Characteristic Curve(ROC) were employed.The value of the Area Under the Curve(AUC) of ROC was above 0.80 for all models.For flood susceptibility modelling, the Dagging model performs superior, followed by RF,the ANN, the SVM, and the RS, then the several benchmark models.The approach and solution-oriented outcomes outlined in this paper will assist state and local authorities as well as policy makers in reducing flood-related threats and will also assist in the implementation of effective mitigation strategies to mitigate future damage.     

Using an extreme learning machine to predict the displacement of step-like landslides in relation to controlling factors

In the evolution of landslides, besides the geological conditions, displacement depends on the variation of the controlling factors. Due to the periodic fluctuation of the reservoir water level and the precipitation, the shape of cumulative displacement-time curves of the colluvial landslides in the Three Gorges Reservoir follows a step function. The Baijiabao landslide in the Three Gorges region was selected as a case study. By analysing the response relationship between the landslide deformation, the rainfall, the reservoir water level and the groundwater level, an extreme learning machine was proposed in order to establish the landslide displacement prediction model in relation to controlling factors. The result demonstrated that the curves of the predicted and measured values were very similar, with a correlation coefficient of 0.984. They showed a distinctive step-like deformation characteristic, which underlined the role of the influencing factors in the displacement of the landslide. In relation to controlling factors, the proposed extreme learning machine (ELM) model showed a great ability to predict the Baijiabao landslide and is thus an effective displacement prediction method for colluvial landslides with step-like deformation in the Three Gorges Reservoir region.     

A novel genetic algorithm for optimization of conditioning factors in shallow translational landslides and susceptibility mapping

Genetic algorithm (GA) is an effective approach in selecting the best factors without considering all possible combinations in landslide susceptibility mapping (LSM). The approach experienced a local optimal solution for hazard mapping. In this study, we propose a novel genetic algorithm (NGA) for solving the problems of optimal precision in selecting conditioning factors based on the crossover and mutation. In the southwestern part of China, including Wenchuan, Ludshan, and Ludian areas, the findings of this study confirm the applicability of NGA, which has a strong robustness compared to GA obviously. Results indicated that the highest area under curve (AUC) of GA is 93.47, 83.45, and 82.21% in Wenchuan, Lushan, and Ludian, respectively. Cumulative error of the precision (?R) is 3.19, 10.48, and 6.05%, and error of the highest precision (?P) is 0.01, 0.03, and 0.12% for Wenchuan, Lushan, and Ludian, respectively. Compared to the GA, the highest accuracy of NGA is 93.48% (Wenchuan), 83.48% (Lushan), and 82.28% (Ludian). It also revealed that ?R is 0.77, 1.26, and 1.82%, and ?P is 0.00, 0.04, and 0.05% for Wenchuan, Lushan, and Ludian, respectively. By comparing with GA, the novel approach of NGA has stronger robustness and higher accuracy on selecting the optimal conditioning factors of landslide. Additionally, the relationship of landslide occurrence with controlling factors was assessed in every study area. According to the results, lithology, distance to roads, elevation, and slope were regarded as the most effective factors for shallow translational landslides. These factors implied that internal structure and composition of rock, anthropogenic activity, and topography factors posed the main impacts on landslide occurrence. Finally, we implemented landslide susceptibility assessment in three study areas. Results showed that high landslide susceptibility was in the east and northeastern parts of Wenchuan; central region northward of Lushan; and southwest, central region, and west of Ludian.     

Bagging-based machine learning algorithms for landslide susceptibility modeling

Natural Hazards - Landslide hazards have attracted increasing public attention over the past decades due to a series of catastrophic consequences of landslide occurrence. Thus, the mitigation and...     

GIS-based weights-of-evidence modelling of rainfall-induced landslides in small catchments for landslide susceptibility mapping

Landslide susceptibility mapping is a vital tool for disaster management and planning development activities in mountainous terrains of tropical and subtropical environments. In this paper, the weights-of-evidence modelling was applied, within a geographical information system (GIS), to derive landslide susceptibility map of two small catchments of Shikoku, Japan. The objective of this paper is to evaluate the importance of weights-of-evidence modelling in the generation of landslide susceptibility maps in relatively small catchments having an area less than 4 sq km. For the study area in Moriyuki and Monnyu catchments, northeast Shikoku Island in west Japan, a data set was generated at scale 1:5,000. Relevant thematic maps representing various factors (e.g. slope, aspect, relief, flow accumulation, soil depth, soil type, land use and distance to road) that are related to landslide activity were generated using field data and GIS techniques. Both catchments have homogeneous geology and only consist of Cretaceous granitic rock. Thus, bedrock geology was not considered in data layering during GIS analysis. Success rates were also estimated to evaluate the accuracy of landslide susceptibility maps and the weights-of-evidence modelling was found useful in landslide susceptibility mapping of small catchments.     

Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin,Asir Region,Saudi Arabia

The current study aimed at evaluating the capabilities of seven advanced machine learning techniques(MLTs),including,Support Vector Machine(SVM),Random Forest(RF),Multivariate Adaptive Regression Spline(MARS),Artificial Neural Network(ANN),Quadratic Discriminant Analysis(QDA),Linear Discriminant Analysis(LDA),and Naive Bayes(NB),for landslide susceptibility modeling and comparison of their performances.Coupling machine learning algorithms with spatial data types for landslide susceptibility mapping is a vitally important issue.This study was carried out using GIS and R open source software at Abha Basin,Asir Region,Saudi Arabia.First,a total of 243 landslide locations were identified at Abha Basin to prepare the landslide inventory map using different data sources.All the landslide areas were randomly separated into two groups with a ratio of 70%for training and 30%for validating purposes.Twelve landslide-variables were generated for landslide susceptibility modeling,which include altitude,lithology,distance to faults,normalized difference vegetation index(NDVI),landuse/landcover(LULC),distance to roads,slope angle,distance to streams,profile curvature,plan curvature,slope length(LS),and slope-aspect.The area under curve(AUC-ROC)approach has been applied to evaluate,validate,and compare the MLTs performance.The results indicated that AUC values for seven MLTs range from 89.0%for QDA to 95.1%for RF.Our findings showed that the RF(AUC=95.1%)and LDA(AUC=941.7%)have produced the best performances in comparison to other MLTs.The outcome of this study and the landslide susceptibility maps would be useful for environmental protection.     

Rainfall-induced landslide susceptibility mapping using machine learning algorithms and comparison of their performance in Hilly area of Fujian Province,China

The rainfall can contribute significantly to landslide events, especially in hilly areas. The landslide susceptibility map (LSM) usually helps to mitigate disasters. However, how to accurately predict the susceptibility of landslides is still a difficult point in the field of disaster research. In this study, five advanced machine learning technologies (MLTs), including the Light Gradient Boosting Machine, extreme gradient boost, categorical boosting (CatBoost), support vector machine, and random forest, are utilized to landslide susceptibility modeling and their capabilities are compared through evaluation indicators. The northern part of Yanping, Fujian Province, China, is selected as the research object, because this area experienced mass landslide events due to extremely heavy rainfall in June 2010, resulting in many casualties and a large number of public facilities destroyed. The influencing factors for landslides, namely topographic, hydrological, geologic and human activities, are prepared from various data sources based on the availability. Through the analysis of the actual situation in the study area, 13 suitable landslide condition factors are considered and the availability of relevant factors is checked according to the multicollinearity test. The landslide inventory including 631 samples in this study area is obtained from historical information, satellite data in Google earth and performed field surveys. The landslide inventory is randomly divided into two datasets for model training and testing with a 7:3 ratio. The area under the curve of ROC, accuracy rate, Kappa index and F1 score are applied to compare the MLTs capabilities. In this paper, the results of factor importance analysis show that the first three important condition factors are the distance to faults, the distance to drainages and the slope. According to the LSMs, in the study area, the central and western regions are at high and very high landslide susceptibility levels, while almost all the eastern and northeastern regions are at medium and low landslide susceptibility levels. The CatBoost model is a very promising technology in landslide research according to the evaluation results, which means that for landslide susceptibility research, gradient boosting algorithms may get more accurate results and show better prospects in the future. Finally, the results of this paper will contribute to environmental protection to a certain extent.

     

MODIS-FIRMS and ground-truthing-based wildfire likelihood mapping of Sikkim Himalaya using machine learning algorithms

Natural Hazards - Wildfires in limited extent and intensity can be a boon for the forest ecosystem. However, recent episodes of wildfires of 2019 in Australia and Brazil are sad reminders of their...     

Flood susceptibility mapping using a geomorphometric approach in South Australian basins

Natural Hazards - Watershed characteristics and their hydrological responses can have severe effects on the occurrence and extent of floods. Therefore, this study focuses on the integration of...     

Predicting permeability of tight carbonates using a hybrid machine learning approach of modified equilibrium optimizer and extreme learning machine

Acta Geotechnica - It is a problematic task to perform petro-physical property prediction of carbonate reservoir rocks in most cases, specifically for permeability prediction since a carbonate rock...     

Comparing classical statistic and machine learning models in landslide susceptibility mapping in Ardanuc (Artvin), Turkey

Natural Hazards - Landslide susceptibility maps provide crucial information that helps local authorities, public institutions, and land-use planners make the correct decisions when they are...