A combined procedure to assess rainfall-induced shallow landslide detachment, transit and runout susceptibility using Machine Learning and GIS techniques

2021 ◽  
Author(s):  
Mariano Di Napoli ◽  
Diego Di Martire ◽  
Domenico Calcaterra ◽  
Marco Firpo ◽  
Giacomo Pepe ◽  
...  
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Shallow Landslide ◽  
Shallow Landslides ◽  
Predisposing Factors ◽  
Mitigation Measures ◽  
Economic Losses ◽  
Meaningful Improvement ◽  
Susceptibility Evaluation ◽  
Landslide Runout

<p>Rainfall-induced landslides are notoriously dangerous phenomena which can cause a notable death toll as well as major economic losses globally. Usually, shallow landslides are triggered by prolonged or severe rainfalls and frequently may evolve into potentially catastrophic flow-like movements. Shallow failures are typical in hilly and mountainous areas due to the combination of several predisposing factors such as slope morphology, geological and structural setting, mechanical properties of soils, hydrological and hydrogeological conditions, land-use changes and wildfires. Because of the ability of these phenomena to travel long distances, buildings and infrastructures located in areas improperly deemed safe can be affected.</p><p>Spatial and temporal hazard posed by flow-like movements is due to both source characteristics (e.g., location and volume) and the successive runout dynamics (e.g., travelled paths and distances). Hence, the assessment of shallow landslide susceptibility has to take into account not only the recognition of the most probable landslide source areas, but also  landslide runout (i.e., travel distance). In recent years, a meaningful improvement in landslide detachment susceptibility evaluation has been gained through robust scientific advances, especially by using statistical approaches. Furthermore, various techniques are available for landslide runout susceptibility assessment in quantitative terms. The combination of landslide detachment and runout dynamics has been admitted by many researchers as a suitable and complete procedure for landslide susceptibility evaluation. However, despite its significance, runout assessment is not as widespread in literature as landslide detachment assessment and still remains a challenge for researchers. Currently, only a few studies focus on the assement of both landslide detachment susceptibility (LDS) and landslide runout susceptibility (LRS).</p><p>In this study, the adoption of a combined approach allowed to estimate shallow landslide susceptibility to both detachment and potential runout. Such procedure is based on the integration between LDS assessment via Machine Learning techniques (applying the Ensemble approach) and LRS assessment through GIS-based tools (using the “reach angle” method). This methodology has been applied to the Cinque Terre National Park (Liguria, north-west Italy), where risk posed by flow-like movements is very high. Nine predisposing factors were chosen, while a database of about 300 rainfall-induced shallow landslides was used as input. In particular, the obtained map may be useful for urban and regional planning, as well as for decision-makers and stakeholders, to predict areas that may be affected by rainfall-induced shallow landslides  in the future and to identify areas where risk mitigation measures are needed.</p>

scholarly journals Rainfall-Induced Shallow Landslide Detachment, Transit and Runout Susceptibility Mapping by Integrating Machine Learning Techniques and GIS-Based Approaches

Water ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 488 ◽  
Author(s):  
Mariano Di Napoli ◽  
Diego Di Martire ◽  
Giuseppe Bausilio ◽  
Domenico Calcaterra ◽  
Pierluigi Confuorto ◽  
...  
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Shallow Landslide ◽  
Shallow Landslides ◽  
Geographical Information ◽  
Machine Learning Techniques ◽  
Mitigation Measures ◽  
Landslide Risk ◽  
Susceptibility Map ◽  
Learning Techniques

Rainfall-induced shallow landslides represent a serious threat in hilly and mountain areas around the world. The mountainous landscape of the Cinque Terre (eastern Liguria, Italy) is increasingly popular for both Italian and foreign tourists, most of which visit this outstanding terraced coastal landscape to enjoy a beach holiday and to practice hiking. However, this area is characterized by a high level of landslide hazard due to intense rainfalls that periodically affect its rugged and steep territory. One of the most severe events occurred on 25 October 2011, causing several fatalities and damage for millions of euros. To adequately address the issues related to shallow landslide risk, it is essential to develop landslide susceptibility models as reliable as possible. Regrettably, most of the current land-use and urban planning approaches only consider the susceptibility to landslide detachment, neglecting transit and runout processes. In this study, the adoption of a combined approach allowed to estimate shallow landslide susceptibility to both detachment and potential runout. At first, landslide triggering susceptibility was assessed using Machine Learning techniques and applying the Ensemble approach. Nine predisposing factors were chosen, while a database of about 300 rainfall-induced shallow landslides was used as input. Then, a Geographical Information System (GIS)-based procedure was applied to estimate the potential landslide runout using the “reach angle” method. Information from such analyses was combined to obtain a susceptibility map describing detachment, transit, and runout. The obtained susceptibility map will be helpful for land planning, as well as for decision makers and stakeholders, to predict areas where rainfall-induced shallow landslides are likely to occur in the future and to identify areas where hazard mitigation measures are needed.

scholarly journals AI-Based Susceptibility Analysis of Shallow Landslides Induced by Heavy Rainfall in Tianshui, China

2021 ◽  
Vol 13 (9) ◽  
pp. 1819
Author(s):  
Tianjun Qi ◽  
Yan Zhao ◽  
Xingmin Meng ◽  
Guan Chen ◽  
Tom Dijkstra
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Heavy Rainfall ◽  
Human Life ◽  
Relative Weight ◽  
Shallow Landslides ◽  
Mitigation Measures ◽  
Slope Aspect ◽  
Economic Damage ◽  
Geological Conditions

Groups of landslides induced by heavy rainfall are widely distributed on a global basis and they usually result in major losses of human life and economic damage. However, compared with landslides induced by earthquakes, inventories of landslides induced by heavy rainfall are much less common. In this study we used high-precision remote sensing images before and after continuous heavy rainfall in southern Tianshui, China, from 20 June to 25 July 2013, to produce an inventory of 14,397 shallow landslides. Based on the results of landslide inventory, we utilized machine learning and the geographic information system (GIS) to map landslide susceptibility in this area and evaluated the relative weight of various factors affecting landslide development. First, 18 variables related to geomorphic conditions, slope material, geological conditions, and human activities were selected through collinearity analysis; second, 21 selected machine learning models were trained and optimized in the Python environment to evaluate the susceptibility of landslides. The results showed that the ExtraTrees model was the most effective for landslide susceptibility assessment, with an accuracy of 0.91. This predictive ability means that our landslide susceptibility results can be used in the implementation of landslide prevention and mitigation measures in the region. Analysis of the importance of the factors showed that the contribution of slope aspect (SA) was significantly higher than that of the other factors, followed by planar curvature (PLC), distance to river (DR), distance to fault (DTF), normalized difference vehicle index (NDVI), distance to road (DTR), and other factors. We conclude that factors related to geomorphic conditions are principally responsible for controlling landslide susceptibility in the study area.

scholarly journals Modeling Shallow Landslide Susceptibility and Assessment of the Relative Importance of Predisposing Factors, through a GIS-Based Statistical Analysis

Geosciences ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 333
Author(s):  
Massimo Conforti ◽  
Fabio Ietto
Keyword(s):  
Landslide Susceptibility ◽  
Shallow Landslide ◽  
Shallow Landslides ◽  
Predisposing Factors ◽  
Susceptibility Map ◽  
Slope Gradient ◽  
Landslide Susceptibility Map ◽  
Jackknife Test ◽  
Susceptibility Model ◽  
Very High

Shallow landslides are destructive hazards and play an important role in landscape processes. The purpose of this paper is to evaluate the shallow landslide susceptibility and to investigate which predisposing factors control the spatial distribution of the collected instability phenomena. The GIS-based logistic regression model and jackknife test were respectively employed to achieve the scopes. The studied area falls in the Mesima basin, located in the southern Calabria (Italy). The research was based mainly on geomorphological study using both interpretation of Google Earth images and field surveys. Thus, 1511 shallow landslides were mapped and 18 predisposing factors (lithology, distance to faults, fault density, land use, soil texture, soil bulk density, soil erodibility, distance to streams, drainage density, elevation, slope gradient, slope aspect, local relief, plan curvature, profile curvature, TPI, TWI, and SPI) were recognized as influencing the shallow landslide susceptibility. The 70% of the collected shallow landslides were randomly divided into a training data set to build susceptibility model and the remaining 30% were used to validate the newly built model. The logistic regression model calculated the landslide probability of each pixel in the study area and produced the susceptibility map. Four classification methods were tested and compared between them, so the most reliable classification system was employed to the shallow landslide susceptibility map construction. In the susceptibility map, five classes were recognized as following: very low, low, moderate, high, and very high susceptibility. About 26.1% of the study area falls in high and very high susceptible classes and most of the landslides mapped (82.4%) occur in these classes. The accuracy of the predictive model was evaluated by using the ROC (receiver operating characteristics) curve approach, which showed an area under the curve (AUC) of 0.93, proving the excellent forecasting ability of the susceptibility model. The predisposing factors importance evaluation, using the jackknife test, revealed that slope gradient, TWI, soil texture and lithology were the most important factors; whereas, SPI, fault density and profile curvature have a least importance. According to these results, we conclude that the shallow landslide susceptibility map can be use as valuable tool both for land-use planning and for management and mitigation of the shallow landslide risk in the study area.

scholarly journals Rainfall-Induced Shallow Landslide Susceptibility Mapping at Two Adjacent Catchments Using Advanced Machine Learning Algorithms

2020 ◽  
Vol 9 (10) ◽  
pp. 569
Author(s):  
Ananta Man Singh Pradhan ◽  
Yun-Tae Kim
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Shallow Landslide ◽  
Machine Learning Algorithms ◽  
Landslide Inventory ◽  
Aerial Photographs ◽  
Landslide Susceptibility Mapping ◽  
Gradient Boosting ◽  
Extreme Gradient Boosting ◽  
Testing Accuracy

Landslides impact on human activities and socio-economic development, especially in mountainous areas. This study focuses on the comparison of the prediction capability of advanced machine learning techniques for the rainfall-induced shallow landslide susceptibility of Deokjeokri catchment and Karisanri catchment in South Korea. The influencing factors for landslides, i.e., topographic, hydrologic, soil, forest, and geologic factors, are prepared from various sources based on availability, and a multicollinearity test is also performed to select relevant causative factors. The landslide inventory maps of both catchments are obtained from historical information, aerial photographs and performed field surveys. In this study, Deokjeokri catchment is considered as a training area and Karisanri catchment as a testing area. The landslide inventories contain 748 landslide points in training and 219 points in testing areas. Three landslide susceptibility maps using machine learning models, i.e., Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN), are prepared and compared. The outcomes of the analyses are validated using the landslide inventory data. A receiver operating characteristic curve (ROC) method is used to verify the results of the models. The results of this study show that the training accuracy of RF is 0.756 and the testing accuracy is 0.703. Similarly, the training accuracy of XGBoost is 0.757 and testing accuracy is 0.74. The prediction of DNN revealed acceptable agreement between the susceptibility map and the existing landslides, with a training accuracy of 0.855 and testing accuracy of 0.802. The results showed that the DNN model achieved lower prediction error and higher accuracy results than other models for shallow landslide modeling in the study area.

scholarly journals A Novel GIS-Based Random Forest Machine Algorithm for the Spatial Prediction of Shallow Landslide Susceptibility

Forests ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 118 ◽  
Author(s):  
Viet-Hung Dang ◽  
Nhat-Duc Hoang ◽  
Le-Mai-Duyen Nguyen ◽  
Dieu Tien Bui ◽  
Pijush Samui
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Landslide Susceptibility ◽  
Spatial Prediction ◽  
Shallow Landslide ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Support Vector ◽  
Conditioning Factors ◽  
Susceptibility Modeling

This study developed and verified a new hybrid machine learning model, named random forest machine (RFM), for the spatial prediction of shallow landslides. RFM is a hybridization of two state-of-the-art machine learning algorithms, random forest classifier (RFC) and support vector machine (SVM), in which RFC is used to generate subsets from training data and SVM is used to build decision functions for these subsets. To construct and verify the hybrid RFM model, a shallow landslide database of the Lang Son area (northern Vietnam) was prepared. The database consisted of 101 shallow landslide polygons and 14 conditioning factors. The relevance of these factors for shallow landslide susceptibility modeling was assessed using the ReliefF method. Experimental results pointed out that the proposed RFM can help to achieve the desired prediction with an F1 score of roughly 0.96. The performance of the RFM was better than those of benchmark approaches, including the SVM, RFC, and logistic regression. Thus, the newly developed RFM is a promising tool to help local authorities in shallow landslide hazard mitigations.

scholarly journals Landslide Susceptibility Mapping at Two Adjacent Catchments Using Advanced Machine Learning Algorithms

2020 ◽  
Author(s):  
Ananta Man Singh Pradhan ◽  
Yun-Tae Kim
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Shallow Landslide ◽  
Machine Learning Algorithms ◽  
Landslide Inventory ◽  
Aerial Photographs ◽  
Landslide Susceptibility Mapping ◽  
Gradient Boosting ◽  
Extreme Gradient Boosting ◽  
Testing Accuracy

Landslides impact on human activities and socio-economic development especially in mountainous areas. This study focuses on the comparison of the prediction capability of advanced machine learning techniques for rainfall-induced shallow landslide susceptibility of Deokjeokri catchment and Karisanri catchment in South Korea. The influencing factors for landslides i.e. topographic, hydrologic, soil, forest, and geologic factors are prepared from various sources based on availability and a multicollinearity test is also performed to select relevant causative factors. The landslide inventory maps of both catchments are obtained from historical information, aerial photographs and performing field survey. In this study, Deokjeokri catchment is considered as a training area and Karisanri catchment as a testing area. The landslide inventories content 748 landslide points in training and 219 points in testing areas. Three landslide susceptibility maps using machine learning models i.e. Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN) are prepared and compared. The outcomes of the analyses are validated using the landslide inventory data. A receiver operating characteristic curve (ROC) method is used to verify the results of the models. The results of this study show that the training accuracy of RF is 0.757 and the testing accuracy is 0.74. Similarly, training accuracy of XGBoost is 0.756 and testing accuracy is 0.703. The prediction of DNN revealed acceptable agreement between susceptibility map and the existing landslides with training and testing accuracy of 0.855 and 0.802, respectively. The results showed that, the DNN model achieved lower prediction error and higher accuracy results than other models for shallow landslide modeling in the study area

scholarly journals Landslide Susceptibility Prediction Considering Regional Soil Erosion Based on Machine-Learning Models

2020 ◽  
Vol 9 (6) ◽  
pp. 377 ◽  
Author(s):  
Faming Huang ◽  
Jiawu Chen ◽  
Zhen Du ◽  
Chi Yao ◽  
Jinsong Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Erosion ◽  
Landslide Susceptibility ◽  
Prediction Accuracy ◽  
Prediction Models ◽  
Research Area ◽  
Predisposing Factors ◽  
Support Vector ◽  
Predisposing Factor ◽  
Operating Feature

Soil erosion (SE) provides slide mass sources for landslide formation, and reflects long-term rainfall erosion destruction of landslides. Therefore, it is possible to obtain more reliable landslide susceptibility prediction results by introducing SE as a geology and hydrology-related predisposing factor. The Ningdu County of China is taken as a research area. Firstly, 446 landslides are obtained through government disaster survey reports. Secondly, the SE amount in Ningdu County is calculated and nine other conventional predisposing factors are obtained under both 30 m and 60 m grid resolutions to determine the effects of SE on landslide susceptibility prediction. Thirdly, four types of machine-learning predictors with 30 m and 60 m grid resolutions—C5.0 decision tree (C5.0 DT), logistic regression (LR), multilayer perceptron (MLP) and support vector machine (SVM)—are applied to construct the landslide susceptibility prediction models considering the SE factor as SE-C5.0 DT, SE-LR, SE-MLP and SE-SVM models; C5.0 DT, LR, MLP and SVM models with no SE are also used for comparisons. Finally, the area under receiver operating feature curve is used to verify the prediction accuracy of these models, and the relative importance of all the 10 predisposing factors is ranked. The results indicate that: (1) SE factor plays the most important role in landslide susceptibility prediction among all 10 predisposing factors under both 30 m and 60 m resolutions; (2) the SE-based models have more accurate landslide susceptibility prediction than the single models with no SE factor; (3) all the models with 30 m resolutions have higher landslide susceptibility prediction accuracy than those with 60 m resolutions; and (4) the C5.0 DT and SVM models show higher landslide susceptibility prediction performance than the MLP and LR models.

scholarly journals Landslide susceptibility assessment based on different machine-learning methods in Zhaoping County of eastern Guangxi

2020 ◽  
Author(s):  
Chunfang Kong ◽  
Kai Xu ◽  
Junzuo Wang ◽  
Chonglong Wu ◽  
Gang Liu
Keyword(s):  
Machine Learning ◽  
Particle Swarm Optimization ◽  
Random Forest ◽  
Landslide Susceptibility ◽  
Roc Curves ◽  
Support Vector ◽  
Swarm Optimization ◽  
Vector Machines ◽  
Susceptibility Evaluation ◽  
Landslide Disaster

Abstract. Regarding the ever increasing and frequent occurrence of serious landslide disaster in eastern Guangxi, the current study were implemented to adopt support vector machines (SVM), particle swarm optimization support vector machines (PSO-SVM), random forest (RF), and particle swarm optimization random forest (PSO-RF) methods to assess landslide susceptibility by Zhaoping County. To this end, 10 landslide disaster-related causal variables including digital elevation model (DEM)-derived, meteorology-derived, Landsat8-derived, geology-derived, and human activities factors were selected for running four machine-learning (ML) methods, and landslide susceptibility evaluation maps were produced. Then, receiver operating characteristics (ROC) curves, and field investigation were performed to verify the efficiency of these models. Analysis and comparison of the results denoted that all four ML models performed well for the landslide susceptibility evaluation as indicated by the values of ROC curves – from 0.863 to 0.934. Moreover, the results also indicated that the PSO algorithm has a good effect on SVM and FR models. In addition, such a result also revealed that the PSO-RF and PSO-SVM models have the strong robustness and stable performance, and those two models are promising methods that could be transferred to other regions for landslide susceptibility evaluation.

scholarly journals Landslide Susceptibility Analysis by Applying TRIGRS to a Reliable Geotechnical Slope Model

Geosciences ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 18
Author(s):  
Mariantonietta Ciurleo ◽  
Settimio Ferlisi ◽  
Vito Foresta ◽  
Maria Clorinda Mandaglio ◽  
Nicola Moraci
Keyword(s):  
Landslide Susceptibility ◽  
Debris Flows ◽  
Input Data ◽  
Southern Italy ◽  
Scientific Literature ◽  
Shallow Landslide ◽  
Shallow Landslides ◽  
Predictive Capability ◽  
Performance Technique

This paper presents the results of a research aimed at analysing the susceptibility to shallow landslides of a study area in the Calabria region (Southern Italy). These shallow landslides, which in some cases evolve as debris flows, periodically affect the study area, causing damage to structures and infrastructure. The involved soils come from the weathering of gneissic rocks and cover about 60% of the study area. To fulfil the goal of the research, the Transient Rainfall Infiltration and Grid-based Slope-Stability (TRIGRS) model was first used, assuming input data (including physical and mechanical parameters of soils) provided by the scientific literature. Then, the preliminary results obtained were used to properly locate in situ investigations that included sampling. Geotechnical laboratory tests allowed characterising the investigated soils, and related parameters were used as new input data of the TRIGRS model. The generated shallow landslide susceptibility scenario showed a good predictive capability based on the adoption of a cutoff-independent performance technique.

scholarly journals Technical Note: Assessing predictive capacity and conditional independence of landslide predisposing factors for shallow landslide susceptibility models

2012 ◽  
Vol 12 (4) ◽  
pp. 979-988 ◽  
Author(s):  
S. Pereira ◽  
J. L. Zêzere ◽  
C. Bateira
Keyword(s):  
Landslide Susceptibility ◽  
Conditional Independence ◽  
Predictive Power ◽  
Slope Angle ◽  
Shallow Landslide ◽  
Technical Note ◽  
Predisposing Factors ◽  
Predictive Capacity ◽  
Susceptibility Model ◽  
Independence Criterion

Abstract. The aim of this study is to identify the landslide predisposing factors' combination using a bivariate statistical model that best predicts landslide susceptibility. The best model is one that has simultaneously good performance in terms of suitability and predictive power and has been developed using variables that are conditionally independent. The study area is the Santa Marta de Penaguião council (70 km2) located in the Northern Portugal. In order to identify the best combination of landslide predisposing factors, all possible combinations using up to seven predisposing factors were performed, which resulted in 120 predictions that were assessed with a landside inventory containing 767 shallow translational slides. The best landslide susceptibility model was selected according to the model degree of fitness and on the basis of a conditional independence criterion. The best model was developed with only three landslide predisposing factors (slope angle, inverse wetness index, and land use) and was compared with a model developed using all seven landslide predisposing factors. Results showed that it is possible to produce a reliable landslide susceptibility model using fewer landslide predisposing factors, which contributes towards higher conditional independence.

Sign in / Sign up

Export Citation Format

Share Document