scholarly journals Improving Voting Feature Intervals for Spatial Prediction of Landslides

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Binh Thai Pham ◽  
Tran Van Phong ◽  
Mohammadtaghi Avand ◽  
Nadhir Al-Ansari ◽  
Sushant K. Singh ◽  
...  
Keyword(s):  
Landslide Susceptibility ◽  
Model Performance ◽  
Spatial Prediction ◽  
Susceptibility Assessment ◽  
Improve Performance ◽  
Landslide Susceptibility Assessment ◽  
Ensemble Techniques ◽  
Susceptibility Maps ◽  
Quantitative Validation ◽  
Two Hybrid

In this study, the main aim is to improve performance of the voting feature intervals (VFIs), which is one of the most effective machine learning models, using two robust ensemble techniques, namely, AdaBoost and MultiBoost for landslide susceptibility assessment and prediction. For this, two hybrid models, namely, AdaBoost-based Voting Feature Intervals (ABVFIs) and MultiBoost-based Voting Feature Intervals (MBVFIs) were developed and validated using landslide data collected from one of the landslide affected districts of Vietnam, namely, Muong Lay. Quantitative validation methods including area under the ROC curve (AUC) were used to evaluate model performance. The results indicated that both the newly developed ensemble models ABVFI (AUC = 0.859) and MBVFI (AUC = 0.839) outperformed the single VFI (AUC = 0.824) model. Thus, ensemble framework-based VFI algorithms can be used for the accurate spatial prediction of landslides, which can also be applied in other landslide prone regions of the world. Landslide susceptibility maps developed by ensemble VFI models can be used for better landslide prevention and risk management of the area.

scholarly journals Susceptibility Assessment for Landslide Initiated along Power Transmission Lines

2021 ◽  
Vol 13 (24) ◽  
pp. 5068
Author(s):  
Shuhao Liu ◽  
Kunlong Yin ◽  
Chao Zhou ◽  
Lei Gui ◽  
Xin Liang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Landslide Susceptibility ◽  
Power Transmission ◽  
Transmission Network ◽  
Power Network ◽  
Susceptibility Assessment ◽  
Multivariate Statistical ◽  
Landslide Susceptibility Assessment ◽  
Susceptibility Maps ◽  
Selection Of

The power network has a long transmission span and passes through wide areas with complex topography setting and various human engineering activities. They lead to frequent landslide hazards, which cause serious threats to the safe operation of the power transmission system. Thus, it is of great significance to carry out landslide susceptibility assessment for disaster prevention and mitigation of power network. We, therefore, undertake an extensive analysis and comparison study between different data-driven methods using a case study from China. Several susceptibility mapping results were generated by applying a multivariate statistical method (logistic regression (LR)) and a machine learning technique (random forest (RF)) separately with two different mapping-units and predictor sets of differing configurations. The models’ accuracies, advantages and limitations are summarized and discussed using a range of evaluation criteria, including the confusion matrix, statistical indexes, and the estimation of the area under the receiver operating characteristic curve (AUROC). The outcome showed that machine learning method is well suitable for the landslide susceptibility assessment along transmission network over grid cell units, and the accuracy of susceptibility models is evolving rapidly from statistical-based models toward machine learning techniques. However, the multivariate statistical logistic regression methods perform better when computed over heterogeneous slope terrain units, probably because the number of units is significantly reduced. Besides, the high model predictive performances cannot guarantee a high plausibility and applicability of subsequent landslide susceptibility maps. The selection of mapping unit can produce greater differences on the generated susceptibility maps than that resulting from the selection of modeling methods. The study also provided a practical example for landslide susceptibility assessment along the power transmission network and its potential application in hazard early warning, prevention, and mitigation.

scholarly journals Novel Credal Decision Tree-Based Ensemble Approaches for Predicting the Landslide Susceptibility

2020 ◽  
Vol 12 (20) ◽  
pp. 3389
Author(s):  
Alireza Arabameri ◽  
Ebrahim Karimi-Sangchini ◽  
Subodh Chandra Pal ◽  
Asish Saha ◽  
Indrajit Chowdhuri ◽  
...  
Keyword(s):  
Decision Tree ◽  
Landslide Susceptibility ◽  
Human Life ◽  
Spatial Relationship ◽  
Model Performance ◽  
Area Under The Curve ◽  
Spatial Prediction ◽  
Susceptibility Maps ◽  
Soft Computing Techniques ◽  
Landslide Susceptibility Maps

Landslides are natural and often quasi-normal threats that destroy natural resources and may lead to a persistent loss of human life. Therefore, the preparation of landslide susceptibility maps is necessary in order to mitigate harmful effects. The key objective of this research is to develop landslide susceptibility maps for the Taleghan basin of Alborz province, Iran, using hybrid Machine Learning (ML) algorithms, i.e., k-fold cross validation and ML techniques of credal decision tree (CDT), Alternative Decision Tree (ADTree), and their ensemble method (CDT-ADTree), which have been state-of-the-art soft computing techniques rarely used in the case of landslide susceptibility assessments. In this study, 22 key landslide causative factors (LCFs) were considered to explore their spatial relationship to landslides, based on local geomorphological and geo-environmental influences. The Random Forest (RF) algorithm was used for the identification of variables importance of different LCFs that are more prone to landslide susceptibility. A receiver operation characteristics (ROC) curve with area under the curve (AUC), accuracy, precision, and robustness index was used to evaluate and compare landslide susceptibility models. The output of the model performance shows that the CDT-ADTree model is the more robust model for the landslide susceptibility where the AUC, accuracy, and precision are 0.981, 0.837, and 0.867, respectively, than the standalone model of CDT and ADTree model. Therefore, it is concluded that the CDT-ADTree ensemble model can be applied as a new promising technique for spatial prediction of the landslide in further studies.

scholarly journals Combined landslide inventory and susceptibility assessment based on different mapping units: an example from the Flemish Ardennes, Belgium

2009 ◽  
Vol 9 (2) ◽  
pp. 507-521 ◽  
Author(s):  
M. Van Den Eeckhaut ◽  
P. Reichenbach ◽  
F. Guzzetti ◽  
M. Rossi ◽  
J. Poesen
Keyword(s):  
Landslide Susceptibility ◽  
Model Performance ◽  
Environmental Information ◽  
Landslide Inventory ◽  
Grid Cells ◽  
Susceptibility Assessment ◽  
Susceptibility Maps ◽  
Validation Set ◽  
Slide Type ◽  
Single Pixel

Abstract. For a 277 km2 study area in the Flemish Ardennes, Belgium, a landslide inventory and two landslide susceptibility zonations were combined to obtain an optimal landslide susceptibility assessment, in five classes. For the experiment, a regional landslide inventory, a 10 m × 10 m digital representation of topography, and lithological and soil hydrological information obtained from 1:50 000 scale maps, were exploited. In the study area, the regional inventory shows 192 landslides of the slide type, including 158 slope failures occurred before 1992 (model calibration set), and 34 failures occurred after 1992 (model validation set). The study area was partitioned in 2.78×106 grid cells and in 1927 topographic units. The latter are hydro-morphological units obtained by subdividing slope units based on terrain gradient. Independent models were prepared for the two terrain subdivisions using discriminant analysis. For grid cells, a single pixel was identified as representative of the landslide depletion area, and geo-environmental information for the pixel was obtained from the thematic maps. The landslide and geo-environmental information was used to model the propensity of the terrain to host landslide source areas. For topographic units, morphologic and hydrologic information and the proportion of lithologic and soil hydrological types in each unit, were used to evaluate landslide susceptibility, including the depletion and depositional areas. Uncertainty associated with the two susceptibility models was evaluated, and the model performance was tested using the independent landslide validation set. An heuristic procedure was adopted to combine the landslide inventory and the susceptibility zonations. The procedure makes optimal use of the available landslide and susceptibility information, minimizing the limitations inherent in the inventory and the susceptibility maps. For the established susceptibility classes, regulations to link terrain domains to appropriate land rules are proposed.

scholarly journals Frequency Ratio Density, Logistic Regression and Weights of Evidence Modelling for Landslide Susceptibility Assessment and Mapping in Yanase and Naka Catchments of Southeast Shikoku, Japan

2020 ◽  
Author(s):  
Matebie Meten ◽  
Netra Prakash Bhandary
Keyword(s):  
Logistic Regression ◽  
Landslide Susceptibility ◽  
Frequency Ratio ◽  
Weights Of Evidence ◽  
Annual Rainfall ◽  
Slope Aspect ◽  
Susceptibility Assessment ◽  
Landslide Susceptibility Assessment ◽  
Susceptibility Maps ◽  
Landslide Susceptibility Maps

Abstract Landslide susceptibility assessment is an important tool for disaster management and development activities. Shikoku Island in the southwest Japan is one of the most landslide prone areas due to heavy typhoon rainfall, complex geology and the presence of mountainous areas and low topographic features (valleys).Yanase and Naka Catchments of Shikoku Island in Japan were chosen as a study area. The objective of this study is to apply Frequency Ratio Densisty (FRD), Logistic Regression (LR) and Weights of Evidence (WoE) models in a GIS environment to prepare the landslide susceptibility maps of this area and select the best one for future infrastructure and landuse planning. Data layers including slope, aspect, profile curvature, plan curvature, lithology, land use, distance from river, distance from fault and annual rainfall were used in this study. In FR method, two models were attempted but the FRD model was found slightly better in its performance. In case of LR method, two models, one with equal proportion and the other with unequal proportion of landslide and non-landslide points were applied and the one with equal proportions was chosen based on its highest performance. A total of five landslide susceptibility maps(LSMs) were produced using FR, LR and WoE models resulting two, two and one LSMs respectively. However, one best model was chosen from the FR and LR methods based on the highest area under the curve (AUC) of the receiver operating characteristic (ROC) curves. This reduced the total number of landslide susceptibility maps to three with the success rates of 86.7%, 86.8% and 80.7% from FRD, LR and WoE models respectively. For validation purpose, all landslides were overlaid over the three landslide susceptibility maps and the percentage of landslides in each susceptibility class was calculated. The percentages of landslides that fall in the high and very high susceptibility classes of FRD, LR and WoE models showed 82%, 84% and 78% respectively. This showed that the LR model with equal proportions of landslides and non-landslide points was slightly better than FRD and WoE models in predicting the probability of future landslide occurrence.

scholarly journals Application of a fast and efficient algorithm to assess landslide prone areas in sensitive clays – toward landslide susceptibility assessment, Sweden

2014 ◽  
Vol 2 (12) ◽  
pp. 7773-7806
Author(s):  
C. Melchiorre ◽  
A. Tryggvason
Keyword(s):  
Landslide Susceptibility ◽  
Model Performance ◽  
Local Information ◽  
Susceptibility Assessment ◽  
National Scale ◽  
Cross Sectional ◽  
Landslide Susceptibility Assessment ◽  
Digital Elevation ◽  
The Relationship ◽  
Filtering Procedure

Abstract. This work deals with susceptibility assessment in sensitive clays at national scale. The proposed methodology is based on a procedure which uses soil data and Digital Elevation Models to detect areas prone to landslides and has been applied in Sweden for several years. Specifically, we tested an algorithm which is able to detect soil and slope criteria guaranteeing a faster execution compared to other implementations and an efficient filtering procedure. The adopted computational solution allows using local information on depth to bedrock and several cross-sectional angle thresholds, and therefore opens up new possibilities to improve landslide susceptibility assessment. We tested the algorithm in the Göta River valley and evaluated the effect of filtering, depth to bedrock and cross-sectional angle thresholds on model performance. The thresholds were derived by analysing the relationship between landslide scarps and the Quick Clay Susceptibility Index (QCSI). The results gave us important insights on how to implement the filtering procedure, the use of depth to bedrock and the derived cross-sectional angle thresholds in landslide susceptibility assessment.

scholarly journals Landslide susceptibility assessment of the part of the North Anatolian Fault Zone (Turkey) by GIS-based frequency ratio and index of entropy models

2016 ◽  
Author(s):  
Gökhan Demir
Keyword(s):  
Fault Zone ◽  
Landslide Susceptibility ◽  
Frequency Ratio ◽  
Susceptibility Assessment ◽  
North Anatolian Fault Zone ◽  
Landslide Susceptibility Assessment ◽  
The North ◽  
Index Of Entropy ◽  
Susceptibility Maps ◽  
Landslide Susceptibility Maps

Abstract. Abstract: In the present study, landslide susceptibility assessment for the the part of the North Anatolian Fault Zone is made using index of entropy models within geographical information system. At first, the landslide inventory map was prepared in the study area using earlier reports, aerial photographs and multiple field surveys. 63 cases (69 %) out of 91 detected landslides were randomly selected for modeling, and the remaining 28 (31 %) cases were used for the model validation. The landslide-trigerring factors, including slope degree, aspect, elevation, distance to faults, distance to streams, distance to road. Subsequently, landslide susceptibility maps were produced using frequency ratio and index of entropy models. For verification, the receiver operating characteristic (ROC) curves were drawn and the areas under the curve (AUC) calculated. The verification results showed that frequency ratio model (AUC = 75.71 %) performed slightly better than index of entropy (AUC = 75.43 %) model. The interpretation of the susceptibility map indicated that distance to streams, distance to road and slope degree play major roles in landslide occurrence and distribution in the study area. The landslide susceptibility maps produced from this study could assist planners and engineers for reorganizing and planning of future road construction.

Discriminant analysis as an efficient method for landslide susceptibility assessment in cities with the scarcity of predisposition data

2021 ◽  
Author(s):  
Cahio Guimarães Seabra Eiras ◽  
Juliana Ribeiro Gonçalves de Souza ◽  
Renata Delicio Andrade de Freitas ◽  
César Falcão Barella ◽  
Tiago Martins Pereira
Keyword(s):  
Discriminant Analysis ◽  
Efficient Method ◽  
Landslide Susceptibility ◽  
Susceptibility Assessment ◽  
Landslide Susceptibility Assessment

scholarly journals Landslide Susceptibility Assessment of Mauritius Island (Indian Ocean)

Geosciences ◽  
2019 ◽  
Vol 9 (12) ◽  
pp. 493 ◽  
Author(s):  
Vincenzo Marsala ◽  
Alberto Galli ◽  
Giorgio Paglia ◽  
Enrico Miccadei
Keyword(s):  
Indian Ocean ◽  
Landslide Susceptibility ◽  
Integrated Approach ◽  
Geographical Information ◽  
Susceptibility Assessment ◽  
Gis Technology ◽  
Mountain Areas ◽  
Landslide Susceptibility Assessment ◽  
Hydrological Hazards ◽  
Mauritius Island

This work is focused on the landslide susceptibility assessment, applied to Mauritius Island. The study area is a volcanic island located in the western part of the Indian Ocean and it is characterized by a plateau-like morphology interrupted by three rugged mountain areas. The island is severely affected by geo-hydrological hazards, generally triggered by tropical storms and cyclones. The landslide susceptibility analysis was performed through an integrated approach based on morphometric analysis and preliminary Geographical Information System (GIS)-based techniques, supported by photogeological analysis and geomorphological field mapping. The analysis was completed following a mixed heuristic and statistical approach, integrated using GIS technology. This approach led to the identification of eight landslide controlling factors. Hence, each factor was evaluated by assigning appropriate expert-based weights and analyzed for the construction of thematic maps. Finally, all the collected data were mapped through a cartographic overlay process in order to realize a new zonation of landslide susceptibility. The resulting map was grouped into four landslide susceptibility classes: low, medium, high, and very high. This work provides a scientific basis that could be effectively applied in other tropical areas showing similar climatic and geomorphological features, in order to develop sustainable territorial planning, emergency management, and loss-reduction measures.

Sign in / Sign up

Export Citation Format

Share Document