Statistical and spatial analysis of landslide susceptibility maps with different classification systems

Baeza, Cristina; Lantada, Nieves; Amorim, Samuel

doi:10.1007/s12665-016-6124-1

Cited by 64 publications

(26 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some classification techniques for a landslide susceptibility map in GIS software, such as manual, defined interval, natural break, equal interval, quantile, standard deviation, geometrical interval, and landslide percentage [118]. Generally, user-defined classification is more difficult for the reader to interpret and justify.…”

Section: Discussionmentioning

confidence: 99%

“…Generally, user-defined classification is more difficult for the reader to interpret and justify. Therefore, current automatic classification systems should be used instead of a user-defined classification [118]. Besides, when landslide susceptibility indexes have positive or negative skewness, the best classification methods are quantile or natural break [119].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

2019

View full text Add to dashboard Cite

The main aim of this study was to compare the performances of the hybrid approaches of traditional bivariate weights of evidence (WoE) with multivariate logistic regression (WoE-LR) and machine learning-based random forest (WoE-RF) for landslide susceptibility mapping. The performance of the three landslide models was validated with receiver operating characteristic (ROC) curves and area under the curve (AUC). The results showed that the areas under the curve obtained using the WoE, WoE-LR, and WoE-RF methods were 0.720, 0.773, and 0.802 for the training dataset, and were 0.695, 0.763, and 0.782 for the validation dataset, respectively. The results demonstrate the superiority of hybrid models and that the resultant maps would be useful for land use planning in landslide-prone areas.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

2019

View full text Add to dashboard Cite

show abstract

“…The poor performance of NB is surprising as it is one of the most widely used and recommended systems (Baeza 2016), but in the present study it is striking for its over-optimistic and unstable classification. This may be due to the data distribution, with large jumps in the tail, which do not correspond with the most appropriate classification levels.…”

Section: Discussionmentioning

confidence: 65%

“…where d (observed agreement) is the proportion of cells in agreement, q is the proportion of agreement expected by chance, and N is the total observations. When categories are ordered it is advisable to use weighted Kappa (Baeza 2016), and assign different weights to categories so that different levels of agreement can contribute to the Kappa value. Although different weights can be used, in the present study the Kappa with linear weighting was calculated in all cases (Fleiss et al 2003).…”

Section: Kappa Index (κ)mentioning

confidence: 99%

A ROC analysis-based classification method for landslide susceptibility maps

et al. 2018

View full text Add to dashboard Cite

A landslide susceptibility map is a crucial tool for land-use spatial planning and management in mountainous areas. An essential issue in such maps is the determination of risk thresholds. To this end, the map is zoned into a limited number of classes. Adopting one classification system or another will not only affect the map's readability and final appearance, but most importantly, it may affect the decision-making tasks required for effective land management. The present study compares and evaluates the reliability of some of the most commonly used classification methods, applied to a susceptibility map produced for the area of La Marina (Alicante, Spain). A new classification method based on ROC analysis is proposed, which extracts all the useful information from the initial dataset (terrain characteristics and landslide inventory) and includes, for the first time, the concept of misclassification costs. This process yields a more objective differentiation of risk levels that relies less on the intrinsic structure of the terrain characteristics. The results reveal a considerable difference between the classification methods used to define the most hazardous zones (in over 20% of the surface) and highlight the need to establish a standard method for producing classified susceptibility maps. The method proposed in the study is particularly notable for its consistency, stability and homogeneity, and may mark the starting point for consensus on a generalisable classification method.

show abstract

“…Some reports with this approach can be found in Amoroso, Totani, and Totani (2011), Riquelme, Cano, Tomás, and Abellán (2016), Saade, Abou-Jaoude, and Wartman (2016) and Rogers and Chung (2017). The second approach depends on measuring the relevance of causative factors by establishing correlations between previous landslides and geoenvironmental variables to predict areas of landslide initiation with a similar combination of factors from local to regional scales (Baeza, Lantada, & Amorim, 2016;Vorpahl, Elsenbeer, Märker, & Schröder, 2012). This is achieved through techniques such as: discriminate analysis, multivariate statistics, frequency ratios, information value method and logistic regression methods (Mahalingam, Olsen, & O'Banion, 2016).…”

Section: Theoretical Frameworkmentioning

confidence: 99%

The potential of PALSAR RTC elevation data for landform semi-automatic detection and landslide susceptibility modeling

Muñoz

Murillo-Feo

Martinez

2018

European Journal of Remote Sensing

View full text Add to dashboard Cite

This study demonstrated the potential of methods derived from geomorphometry and regression models to evaluate landslide susceptibility in a study area located in southern Colombia. From a morphometric stance, the first step was to evaluate the quality of DEM sources by comparison to control points obtained by static-mode GPS. The PALSAR_RTC_hi data was selected for having the best accuracy of heights and was used to derivate terrain parameters at SAGA software. Then, the Principal Component Analysis selected variables with low collinearity, and we classified twelve landforms using fuzzy k-means algorithm, which was compared to a geomorphological map by using the multinomial logistic regression method in R software. We got a Kappa coincidence index of about 30%. The resulting landslide susceptibility mapping took dependent (a mask with unstable-stable cells from an existing landslide inventory) and independent variables (selected morphometric ones). The binary logistic regression showed the propensity of the area to be adversely affected by landslides. This model's performance was tested with a ROC curve over a sample, with 20% of landslide database resulting in an Area Under the Curve of 0,55. This result was contrasted with a spatial prediction model of debris flow, explaining the high frequency of avalanches.

show abstract

Statistical and spatial analysis of landslide susceptibility maps with different classification systems

Cited by 64 publications

References 27 publications

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models

A ROC analysis-based classification method for landslide susceptibility maps

The potential of PALSAR RTC elevation data for landform semi-automatic detection and landslide susceptibility modeling

Contact Info

Product

Resources

About