Rainfall-induced Landslide Susceptibility Research Articles

Exploring Bayesian network model with noise filtering for rainfall-induced landslide susceptibility assessment in Fujian, China

Exploring Bayesian network model with noise filtering for rainfall-induced landslide susceptibility assessment in Fujian, China

Comparative Analysis of Machine Learning, Statistical, and MCDA Methods for Rainfall-Induced Landslide Susceptibility Mapping in the Eco-Sensitive Koyna River Basin of India

Comparative Analysis of Machine Learning, Statistical, and MCDA Methods for Rainfall-Induced Landslide Susceptibility Mapping in the Eco-Sensitive Koyna River Basin of India

Probabilistic and physically-based modelling of rainfall-induced landslide susceptibility using integrated GIS-FORM algorithm

Probabilistic and physically-based modelling of rainfall-induced landslide susceptibility using integrated GIS-FORM algorithm

Rainfall-Induced Landslide Susceptibility Assessment and the Establishment of Early Warning Techniques at Regional Scale

This study builds upon deterministic evaluations of the extensive cumulative rainfall thresholds associated with shallow landslides in the Gaoping River Basin, with a specific focus on the necessary response times during typhoon and intense rainfall events. Following the significant impact of Typhoon Morakot on the Liugui area, our investigation enhances previous research by employing a downscaled approach. We aim to establish early warning models for village-level, intermediate-scale landslide cumulative rainfall thresholds and to create action thresholds for small-scale, key landslide-prone slopes. Our inquiry not only combines various analytical models but also validates their reliability through comprehensive case studies. Comparative analysis with the empirical values set by the Soil and Water Conservation Bureau (SWCB) and the National Center for Disaster Reduction (NCDR) provides a median response time of 6 h, confirming that our findings are consistent with the response time frameworks established by these institutions, thus validating their effectiveness for typhoon-related landslide alerts. The results not only highlight the reference value of applying downscaled cumulative rainfall thresholds at the village level but also emphasize the significance of the evaluated warning thresholds as viable benchmarks for early warnings in landslide disaster management during Taiwan’s flood and typhoon seasons. This research offers a refined methodological approach to landslide early warning systems and provides scientific support for decision making by local governments and disaster response teams.

Quantification of climate change impact on rainfall-induced shallow landslide susceptibility: a case study in central Norway

ABSTRACT Climate change impact on rainfall-induced landslide susceptibility of a certain region is often implied based on expected changes in rainfall patterns and rarely explicitly quantified. This study aims to address this gap by implementing coupled landslide and climate modelling chains to explicitly assess the effects of changing rainfall patterns on rainfall-induced landslide susceptibility. The effects of climate change are integrated into the landslide modelling chain via Intensity-Duration-Frequency (IDF) curves for the present and future climate conditions for a landslide-prone study area located in central Norway. The effects of climate change on landslide susceptibility are examined by using a physical-based landslide prediction model with rainfall events of varying duration and intensity that are simulated based on the climate-dependent IDF curves. The novelty of this study is the proposition of a novel probabilistic framework to assess the climate change impact on landslide susceptibility for rainfall events with a given duration. The proposed framework accounts for both the uncertainties of rainfall events through probabilistic interpretation of IDF curves and the uncertainties in the landslide model with the Monte Carlo method. Compared to results based on only intense rainfall events, the proposed framework leads to a lower increase in the probability of landslide initiation and landslide-susceptible extents due to climate change.

Dynamic rainfall-induced landslide susceptibility: A step towards a unified forecasting system

The initial inception of the landslide susceptibility concept defined it as a static property of the landscape, explaining the proneness of certain locations to generate slope failures. Since the spread of data-driven probabilistic solutions though, the original susceptibility definition has been challenged to incorporate dynamic elements that would lead the occurrence probability to change both in space and in time. This is the starting point of this work, which combines the traditional strengths of the susceptibility framework together with the strengths typical of landslide early warning systems. Specifically, we model landslide occurrences in the norther sector of Vietnam, using a multi-temporal landslide inventory recently released by NASA. A set of static (terrain) and dynamic (cumulated rainfall) covariates are selected to explain the landslide presence/absence distribution via a Bayesian version of a binomial Generalized Additive Models (GAM). Thanks to the large spatiotemporal domain under consideration, we include a large suite of cross-validation routines, testing the landslide prediction through random sampling, as well as through stratified spatial and temporal sampling. We even extend the model test towards regions far away from the study site, to be used as external validation datasets. The overall performance appears to be quite high, with Area Under the Curve (AUC) values in the range of excellent model results, and very few localized exceptions.This model structure may serve as the basis for a new generation of early warning systems. However, the use of The Climate Hazards group Infrared Precipitation with Stations (CHIRPS) for the rainfall component limits the model ability in terms of future prediction. Therefore, we envision subsequent development to take this direction and move towards a unified dynamic landslide forecast. Ultimately, as a proof-of-concept, we have also implemented a potential early warning system in Google Earth Engine.

Framework for risk assessment of economic loss from structures damaged by rainfall-induced landslides using machine learning

ABSTRACT Given the increased frequency of extreme rainfall events, pre-disaster countermeasures against landslides triggered by heavy rainfall are important to enhance disaster resilience. This study presents a methodology for economic risk assessment of structures affected by rainfall-induced landslides using machine learning (ML). Random Forest and LightGBM algorithms were applied to develop ML-based landslide prediction models considering the spatial distributions of landslide conditioning and triggering factors. The rainfall index was calculated considering the temporal variation in rainfall and was used as a feature associated with rainfall intensity. The rainfall hazard curve, representing the relationship between the rainfall index and its annual exceedance probability, was statistically estimated using a generalised extreme value distribution. Rainfall-induced landslide susceptibility was assessed using an ML-based landslide prediction model and rainfall hazard curve. Finally, the risk curve associated with the economic loss from structures damaged by rainfall-induced landslides was estimated based on landslide susceptibility and structure distribution maps. In this study, LightGBM showed better prediction performance for evaluating rainfall-induced landslide susceptibility than Random Forest. An illustrative example is presented to demonstrate that the proposed methodology can be used to develop an appropriate risk-based disaster mitigation strategy.

A free web-based approach for rainfall-induced landslide susceptibility modeling: Case study of Clearwater National Forest, Idaho, USA

This study presents an interactive web-based approach for modeling rainfall-induced landslide susceptibility using Free Open Source Software (FOSS). The design is based on the R statistical framework and Shiny package coupled with the shallow slope stability model (SHALSTAB) from SAGA GIS. The easy-to-use real-time application extends the potential of current modeling efforts to non-expert R and GIS users and can also be used in an educational context for classroom teaching activity and enabling research-informed learning. The parsimonious approach (i.e. few parameter inputs) is accomplished in two sequential steps including modeling and validation by the use of site-specific datasets. The approach was tested in a case study on the Clearwater National Forest and the results from the validation showed an overall accuracy of 0.894, kappa of 0.789 and AUC from ROC curve was 0.715. The modeled landslide potential may be used as a decision-support tool for local planning.

Global Dynamic Rainfall-Induced Landslide Susceptibility Mapping Using Machine Learning

Precipitation is the main factor that triggers landslides. Rainfall-induced landslide susceptibility mapping (LSM) is crucial for disaster prevention and disaster losses mitigation, though most studies are temporally ambiguous and on a regional scale. To better reveal landslide mechanisms and provide more accurate landslide susceptibility maps for landslide risk assessment and hazard prediction, developing a global dynamic LSM model is essential. In this study, we used Google Earth Engine (GEE) as the main data platform and applied three tree-based ensemble machine learning algorithms to construct global, dynamic rainfall-induced LSM models based on dynamic and static landslide influencing factors. The dynamic perspective is used in LSM: dynamic changes in landslide susceptibility can be identified on a daily scale. We note that Random Forest algorithm offers robust performance for accurate LSM (AUC = 0.975) and although the classification accuracy of LightGBM is the highest (AUC = 0.977), the results do not meet the sufficient conditions of a landslide susceptibility map. Combined with quantitative precipitation products, the proposed model can be used for the release of historical and predictive global dynamic landslide susceptibility information.

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

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

Assessment of rainfall-induced landslide susceptibility in Artvin, Turkey using machine learning techniques

In this study, the performances of machine learning models, such as artificial neural networks (ANN), gradient-boosting machines (GBM), random forest (RF) and support vector machines (SVM) in rainfall-induced landslide susceptibility mapping were evaluated. For this purpose, the Arhavi, Hopa and Kemalpaşa districts of Artvin, which is one of the highest rainfall areas in Turkey, were identified as the study area. A landslide inventory comprising 533 landslide polygons (3959 pixels at 10-m resolution) was used; 70% of the pixels showing the landslides were used for training the models and the remaining 30% were used to validate the models. For landslide susceptibility modelling, 13 factors associated with landslides were considered. The area under the receiver operating characteristic curve was found to reveal the predictive capabilities of the models. As a result, the prediction rates of the ANN, SVM, RF and GBM models were found to be 93.8%, 94.8%, 96.1%, and 97%, respectively. According to the results, the GBM outperformed other models.

Impact of Rainfall-Induced Landslide Susceptibility Risk on Mountain Roadside in Northern Thailand

Landslide incidents frequently occur in the upper northern region of Thailand due to its topography, which is mostly mountainous with high slopes. In the past, when landslides happened in this area, they affected traffic accessibility for rescue and evacuation. For this reason, if the risk of landslides could be evaluated, it would help in the planning of preventive measures to mitigate the damage. This study was carried out to create and develop a risk estimation model using the artificial neural network (ANN) technique for landslides at the edge of the roadside, by collecting field data on past landslides in the study areas in Chiang Rai and Chiang Mai Provinces. A total of 9602 data points were collected. The variables for forecasting were: (1) land cover, (2) physiographic features, (3) slope angle, and (4) five-day cumulative rainfall. Two hidden layers were used to create the model. The number of nodes in the first and second hidden layers were five and one, respectively, which were derived from a total of 25 trials, and the highest accuracy achieved was 96.74%. When applying the model, a graph demonstrating the relationship between the landslide risk, rainfall, and the slopes of the road areas was obtained. The results show that high slopes result in more landslides than low slopes, and that rainfall is a major trigger for landslides on roads. The outcomes of the study could be used to create risk maps and provide information for developing warnings for high-slope mountain roads in the upper northern region of Thailand.

GIS based assessment of rainfall-induced landslide susceptibility of sensitive marine clays: a case study

ABSTRACT Landslides are frequent occurrences in Ottawa, Canada because sensitive marine clays (also known as Leda clay or Champlain Sea clay) dominate the landscape. These landslides are often triggered by rainfall in the region. A geographic information system (GIS) based modelling approach has been developed to assess and predict rainfall-induced landslides in the sensitive clays of the Ottawa region. The Transient Rainfall Infiltration and Grid-based Slope-stability (TRIGRS) model has been used in a GIS framework to investigate the influence of rainfall On shallow landslides over the Ottawa region, with respect to time and location. The assessment result maps show that the steep slopes of sensitive clays are more prone to landslides. Furthermore, susceptibility to landslides in these areas increases with long periods of intense rainfall. The proposed GIS based model is validated by comparing the predicted areas of landslides induced by rainfall with previous shallow landslides that had occurred in the Ottawa region. The results show that there is a good agreement between the predicted areas of landslides and the previous landslides reported. The proposed GIS–TRIGRS combined modelling approach can be therefore considered as a potential tool for assessing and predicting rainfall induced landslides in sensitive marine clays in Ottawa.

Capturing the footprints of ground motion in the spatial distribution of rainfall-induced landslides

The coupled effect of earthquakes and rainfall is rarely investigated in landslide susceptibility assessments although it could be crucial to predict landslide occurrences. This is even more critical in the context of early warning systems and especially in cases of extreme precipitation regimes in post-seismic conditions, where the rock masses are already damaged due to the ground shaking. Here, we investigate this concept by accounting for the legacy of seismic ground shaking in rainfall-induced landslide (RFIL) scenarios. We do this to identify whether ground shaking plays a role in the susceptibility to post-seismic rainfall-induced landslides and to identify whether this legacy effect persists through time. With this motivation, we use binary logistic regression and examine time series of landslides associated with four earthquakes occurred in Indonesia: 2012 Sulawesi (Mw = 6.3), 2016 Reuleut (Mw = 6.5), 2017 Kasiguncu (Mw = 6.6) and 2018 Palu (Mw = 7.5) earthquakes. The dataset includes one co-seismic and three post-seismic landslide inventories for each earthquake. We use the peak ground acceleration map of the last strongest earthquake in each case as a predisposing factor of landslides representing the effect of ground shaking. We observe that, at least for the study areas under consideration and in a probabilistic context, the earthquake legacy contributes to increase the post-seismic RFIL susceptibility. This positive contribution decays through time. Specifically, we observe that ground motion is a significant predisposing factor controlling the spatial distribution of RFIL in the post-seismic period 110 days after an earthquake. We also show that this effect dissipates within 3 years at most.

Fast physically-based model for rainfall-induced landslide susceptibility assessment at regional scale

Rainfall-induced landslides represent an important threat in mountainous areas. Therefore, a physically-based model called “Fast Shallow Landslide Assessment Model” (FSLAM) was developed to calculate large areas (>100 km2) with a high-resolution topography in a very short computational time. FSLAM applies a simplified hydrological model and the infinite slope theory, while the two most sensitive soil properties regarding slope stability (cohesion and friction angle) can be stochastically included. The model has five necessary input raster files including information of soil properties, vegetation, elevation and rainfall. The principal output is the probability of failure (PoF) map. The Principality of Andorra was selected as case study, where FSLAM was successfully applied and validated using the existing landslide inventory. The PoF raster file of Andorra (including 19 million cells) was calculated in only 2 min. Therefore, an accurate calibration of the input parameters was easy, which strongly improved the final outcomes.

Torrential rainfall-induced landslide susceptibility assessment using machine learning and statistical methods of eastern Himalaya

Landslide susceptibility predictive capabilities are believed to be varied with numerous techniques such as stand-alone statistical, stand-alone machine learning (ML), and ensemble of statistical and ML. However, the landslide susceptibility (LS) model is constantly being modified with recent progress in statistics and in ML. We used logistic regression (LR), random forest (RF), boosted regression tree (BRT), BRT-LR, and BRT-RF model for model calibration and validation. Apart from that, we used RF to measure the relative importance of landslide causative factors (LCFs). Tests were conducted to the damaged landslide patches using a number of 16 LCFs (geomorphological, hydrological, geological, and environmental). We noticed that the predicted rates are exceptional for the BRT-RF model (AUC: 0.919), whereas models of LR (0.822), RF (0.876), BRT (0.857), and BRT-LR (0.902) produced higher variations in the data set accuracy. We therefore propose that the BRT-RF model be an effective method of increasing predictive precision level of LS. This research finding can be used in other fields for planning and management by stakeholders in order to minimize the impact of landslide.

Risk Assessment of Resources Exposed to Rainfall Induced Landslide with the Development of GIS and RS Based Ensemble Metaheuristic Machine Learning Algorithms

Disastrous natural hazards, such as landslides, floods, and forest fires cause a serious threat to natural resources, assets and human lives. Consequently, landslide risk assessment has become requisite for managing the resources in future. This study was designed to develop four ensemble metaheuristic machine learning algorithms, such as grey wolf optimized based artificial neural network (GW-ANN), grey wolf optimized based random forest (GW-RF), particle swarm optimization optimized based ANN (PSO-ANN), and PSO optimized based RF for modeling rainfall-induced landslide susceptibility (LS) in Aqabat Al-Sulbat, Asir region, Saudi Arabia, which observes landslide frequently. To obtain very high precision and robust prediction from machine learning algorithms, the grey wolf and PSO optimization algorithms were integrated to develop new ensemble machine learning techniques. Subsequently, LS maps produced by training dataset were validated using the receiver operating characteristics (ROC) curve based on the testing dataset. Based on the area under curve (AUC) value of ROC curve, the best method for LS modeling was selected. We developed ROC curve-based sensitivity analysis to investigate the influence of the parameters for LS modeling. The Gumble extreme value distribution was employed to estimate the rainfall at 2, 5, 10, 20, 50, and 100 year return periods. Then, the landslide hazard maps were prepared at different return periods by integrating the best LS model and estimated rainfall at different return periods. The theory of danger pixels was employed to prepare a final risk assessment of the resources, which have been exposed to the landslide. The results showed that 27–42 and 6–15 km2 were predicted as the very high and high LS zones using four ensemble metaheuristic machine learning algorithms. Based on the area under curve (AUC) of ROC, GR-ANN (AUC-0.905) appeared as the best model for LS modeling. The areas under high and very high landslide hazard were gradually increased over the progression of time (26 km2 at the 2 year return period and 40 km2 at the 100 year return period for the high landslide hazard zone, and 6 km2 at the 2 year return period and 20 km2 at the 100 year return period for the very high landslide hazard zone). Similarly, the areas of danger pixel also increased gradually from the 2 to 100 year return periods (37 km2 to 62 km2). Various natural resources, such as scrubland, built up, and sparse vegetation, were identified under risk zone due to landslide hazards. In addition, these resources would be exposed extensively to landslides over the advancement of return periods. Therefore, the outcome of the present study will help planners and scientists to propose high precision management plans for protecting natural resources, which have been exposed to landslides.

An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan

BackgroundLandslide-affecting factors are uncorrelated or non-linearly correlated, limiting the predictive performance of traditional machine learning methods for landslide susceptibility assessment. Deep learning methods can take advantage of the high-level representation and reconstruction of information from landslide-affecting factors. In this paper, a novel deep learning-based algorithm that combine classifiers of both deep learning and machine learning is proposed for landslide susceptibility assessment. A stacked autoencoder (StAE) and a sparse autoencoder (SpAE) both consist of an input layer for raw data, hidden layer for feature extraction, and output layer for classification and prediction. As a study case, Oda City and Gotsu City in Shimane Prefecture, southwestern Japan, were used for susceptibility assessment and prediction of landslides triggered by extreme rainfall.ResultsThe prediction performance was compared by analyzing real landslide and non-landslide data. The prediction performance of random forest (RF) was evaluated as better than that of a support vector machine (SVM) in traditional machine learning, so RF was combined with both StAE and SpAE. The results show that the prediction ratio of the combined classifiers was 93.2% for StAE combined with RF model and 92.5% for SpAE combined with RF model, which were higher than those of the SVM (87.4%), RF (89.7%), StAE (84.2%), and SpAE (88.2%).ConclusionsThis study provides an example of combined classifiers giving a better predictive ratio than a single classifier. The asymmetric and unsupervised autoencoder combined with RF can exploit optimal non-linear features from landslide-affecting factors successfully, outperforms some conventional machine learning methods, and is promising for landslide susceptibility assessment.

GIS-based logistic regression for rainfall-induced landslide susceptibility mapping under different grid sizes in Yueqing, Southeastern China

The logistic regression (LR) method was applied to assess landslide susceptibility in the northern Yueqing of Zhejiang Province, China. An inventory map of 323 landslides, digital elevation models (DEMs), remote sensing images, geological map, roads and rivers were collected and utilized in the analysis. LR models using partially continuous (LR-CON) and all categorized variables (LR-CAT) were carried out under different grid sizes of 5 m, 15 m and 30 m to investigate the influence of variable type and grid size on landslide susceptibility assessment. Ten different subsets of positive (landslide) and negative (non-landslide) cases were prepared for each kind of LR models. Receiver operation characteristic (ROC) curves were employed to evaluate the performance of the LR models while cross-validation was used to validate the effectiveness of susceptibility maps. The models with and without the rainfall factor were also compared. Among the three grid sizes, the result of 15 m shows the best performance with mean AUC (the area under a ROC curve) of 82.6%. The AUC values of LR-CON models with different grid sizes all demonstrated acceptable fit (0.7 < mean AUC <0.8) while those of LR-CAT models showed an excellent fit (mean AUC > 0.8), indicating that LR method has a better performance when using all categorical variables than using partially continuous variables. Random sampling is an adoptable method to generate training group and there is no significant difference of AUC values among different data subsets. The results also showed that the accuracy of the landslide susceptibility models is higher when rainfall is included in the analyses.

Evaluating GIS-Based Multiple Statistical Models and Data Mining for Earthquake and Rainfall-Induced Landslide Susceptibility Using the LiDAR DEM

Landslides are typically triggered by earthquakes or rainfall occasionally a rainfall event followed by an earthquake or vice versa. Yet, most of the works presented in the past decade have been largely focused at the single event-susceptibility model. Such type of modeling is found insufficient in places where the triggering mechanism involves both factors such as one found in the Chuetsu region, Japan. Generally, a single event model provides only limited enlightenment of landslide spatial distribution and thus understate the potential combination-effect interrelation of earthquakes- and rainfall-triggered landslides. This study explores the both-effect of landslides triggered by Chuetsu-Niigata earthquake followed by a heavy rainfall event through examining multiple traditional statistical models and data mining for understanding the coupling effects. This paper aims to compare the abilities of the statistical probabilistic likelihood-frequency ratio (PLFR) model, information value (InV) method, certainty factors (CF), artificial neural network (ANN) and ensemble support vector machine (SVM) for the landslide susceptibility mapping (LSM) using high-resolution-light detection and ranging digital elevation model (LiDAR DEM). Firstly, the landslide inventory map including 8459 landslide polygons was compiled from multiple aerial photographs and satellite imageries. These datasets were then randomly split into two parts: 70% landslide polygons (5921) for training model and the remaining polygons for validation (2538). Next, seven causative factors were classified into three categories namely topographic factors, hydrological factors and geological factors. We then identified the associations between landslide occurrence and causative factors to produce LSM. Finally, the accuracies of five models were validated by the area under curves (AUC) method. The AUC values of five models vary from 0.77 to 0.87. Regarding the capability of performance, the proposed SVM is promising for constructing the regional landslide-prone potential areas using both types of landslides. Additionally, the result of our LSM can be applied for similar areas which have been experiencing both rainfall-earthquake landslides.