Landslide susceptibility mapping using geographically-weighted principal component analysis

Sabokbar, H A Faraji; Roodposhti, Majid Shadman; Tazik, Esmaeil

doi:10.1016/j.geomorph.2014.07.026

Cited by 93 publications

(33 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The idea of implementing an integration method for LS zonation is not new. Recent examples are the efforts of [90][91][92]. In the first study, AHP and fuzzy sets were combined to determine LS levels for areas of the Metro Vancouver region, British Columbia, Canada.…”

Section: Discussionmentioning

confidence: 99%

Integrating Expert Knowledge with Statistical Analysis for Landslide Susceptibility Assessment at Regional Scale

et al. 2016

View full text Add to dashboard Cite

In this paper, an integration landslide susceptibility model by combining expert-based and bivariate statistical analysis (Landslide Susceptibility Index-LSI) approaches is presented. Factors related with the occurrence of landslides-such as elevation, slope angle, slope aspect, lithology, land cover, Mean Annual Precipitation (MAP) and Peak Ground Acceleration (PGA)-were analyzed within a GIS environment. This integrated model produced a landslide susceptibility map which categorized the study area according to the probability level of landslide occurrence. The accuracy of the final map was evaluated by Receiver Operating Characteristics (ROC) analysis depending on an independent (validation) dataset of landslide events. The prediction ability was found to be 76% revealing that the integration of statistical analysis with human expertise can provide an acceptable landslide susceptibility assessment at regional scale.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrating Expert Knowledge with Statistical Analysis for Landslide Susceptibility Assessment at Regional Scale

et al. 2016

View full text Add to dashboard Cite

show abstract

“…These types of models perform very well for LSP in many research areas due to their advantages in supervised data mining [33]. The frequently used USML models include K-means model [34,35], self-organization mapping (SOM) model [15,36], principal component analysis [37,38], hierarchical cluster analysis [39], and so on. These models have also been widely used in LSP because the modeling process is simple [40].…”

Section: Introductionmentioning

confidence: 99%

Landslide Susceptibility Prediction Based on Remote Sensing Images and GIS: Comparisons of Supervised and Unsupervised Machine Learning Models

et al. 2020

View full text Add to dashboard Cite

Landslide susceptibility prediction (LSP) has been widely and effectively implemented by machine learning (ML) models based on remote sensing (RS) images and Geographic Information System (GIS). However, comparisons of the applications of ML models for LSP from the perspectives of supervised machine learning (SML) and unsupervised machine learning (USML) have not been explored. Hence, this study aims to compare the LSP performance of these SML and USML models, thus further to explore the advantages and disadvantages of these ML models and to realize a more accurate and reliable LSP result. Two representative SML models (support vector machine (SVM) and CHi-squared Automatic Interaction Detection (CHAID)) and two representative USML models (K-means and Kohonen models) are respectively used to scientifically predict the landslide susceptibility indexes, and then these prediction results are discussed. Ningdu County with 446 recorded landslides obtained through field investigations is introduced as case study. A total of 12 conditioning factors are obtained through procession of Landsat TM 8 images and high-resolution aerial images, topographical and hydrological spatial analysis of Digital Elevation Modeling in GIS software, and government reports. The area value under the curve of receiver operating features (AUC) is applied for evaluating the prediction accuracy of SML models, and the frequency ratio (FR) accuracy is then introduced to compare the remarkable prediction performance differences between SML and USML models. Overall, the receiver operation curve (ROC) results show that the AUC of the SVM is 0.892 and is slightly greater than the AUC of the CHAID model (0.872). The FR accuracy results show that the SVM model has the highest accuracy for LSP (77.80%), followed by the CHAID model (74.50%), the Kohonen model (72.8%) and the K-means model (69.7%), which indicates that the SML models can reach considerably better prediction capability than the USML models. It can be concluded that selecting recorded landslides as prior knowledge to train and test the LSP models is the key reason for the higher prediction accuracy of the SML models, while the lack of a priori knowledge and target guidance is an important reason for the low LSP accuracy of the USML models. Nevertheless, the USML models can also be used to implement LSP due to their advantages of efficient modeling processes, dimensionality reduction and strong scalability.

show abstract

“…The present method was based on a previous approach [19], which is currently the most widely applied due to its performance and possibility of being converted into appropriate spatial maps of landslide susceptibility [20][21][22].…”

Section: Reference Methodsmentioning

confidence: 99%

Intrinsic Environmental Vulnerability as Shallow Landslide Susceptibility in Environmental Impact Assessment

Turconi

Luino

Gussoni³

et al. 2019

Sustainability

View full text Add to dashboard Cite

This work investigated the susceptibility factors that trigger shallow landslides. In particular, the objective of the research was the implementation of a method to determine the relevant factors that can trigger shallow landslide events. However, with respect to the existing methods, the integration with historical datasets and the inclusion of spatial factors displaying dynamics in the same characteristic timescales were specific features of the developed tool. The study area included the watersheds of the Sessera and Strona rivers in the alpine area of the Province of Biella (Piedmont, NW Italy). The method was developed and tested from two sub-datasets derived from an integrated dataset that referred to an intense event, involving the same area, that occurred in 1968 (2–3 November). This allowed the implementation of an integrated representation of landslides’ predisposing factors and the identification and classification in different groups of the areas susceptible to geo-hydrological instability processes. The previously existing databases were verified and integrated into a geographic information system (GIS) environment, giving a potentially sharable source of information for planning purposes. The obtained maps represent a metric of one of the possible intrinsic environmental vulnerability factors for the area under study. Consequently, this method can represent a future instrument for determining the intrinsic environmental vulnerability dependent on landslides within an environmental impact assessment (EIA), as required by the most recent European regulation on EIA. Moreover, the shared information can be used to implement informed policy and planning processes, based on a bottom-up approach. In particular, the availability online of landslide susceptibility maps could support the generation of augmented information—useful for both local administrators and planners as well as for stakeholders willing to implement specific projects or infrastructure in vulnerable areas, such as mountains.

show abstract

Landslide susceptibility mapping using geographically-weighted principal component analysis

Cited by 93 publications

References 51 publications

Integrating Expert Knowledge with Statistical Analysis for Landslide Susceptibility Assessment at Regional Scale

Integrating Expert Knowledge with Statistical Analysis for Landslide Susceptibility Assessment at Regional Scale

Landslide Susceptibility Prediction Based on Remote Sensing Images and GIS: Comparisons of Supervised and Unsupervised Machine Learning Models

Intrinsic Environmental Vulnerability as Shallow Landslide Susceptibility in Environmental Impact Assessment

Contact Info

Product

Resources

About