GIS-based logistic regression for landslide susceptibility mapping of the Zhongxian segment in the Three Gorges area, China

Bai, Shibiao; Wang, Jian; Lv, Guonian; Zhou, Pinggen; Hou, Shugui; Xu, Shiqiang

doi:10.1016/j.geomorph.2009.09.025

Cited by 432 publications

(256 citation statements)

References 33 publications

Supporting

Mentioning

222

Contrasting

Unclassified

Order By: Relevance

“…The fact that landslide explanatory factors can be included in the model as either categorical or continuous variables gives logistic regression models a great advantage over multiple regression models, which can only include continuous variables. Finally, logistic regression models can be used to draw susceptibility maps when combined with GIS (Lee, 2005;Bai et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

Landslide susceptibility mapping on a global scale using the method of logistic regression

Lin

Wang

2017

Nat. Hazards Earth Syst. Sci.

117

View full text Add to dashboard Cite

Abstract. This paper proposes a statistical model for mapping global landslide susceptibility based on logistic regression. After investigating explanatory factors for landslides in the existing literature, five factors were selected for model landslide susceptibility: relative relief, extreme precipitation, lithology, ground motion and soil moisture. When building the model, 70 % of landslide and nonlandslide points were randomly selected for logistic regression, and the others were used for model validation. To evaluate the accuracy of predictive models, this paper adopts several criteria including a receiver operating characteristic (ROC) curve method. Logistic regression experiments found all five factors to be significant in explaining landslide occurrence on a global scale. During the modeling process, percentage correct in confusion matrix of landslide classification was approximately 80 % and the area under the curve (AUC) was nearly 0.87. During the validation process, the above statistics were about 81 % and 0.88, respectively. Such a result indicates that the model has strong robustness and stable performance. This model found that at a global scale, soil moisture can be dominant in the occurrence of landslides and topographic factor may be secondary.

show abstract

Section: Introductionmentioning

confidence: 99%

Landslide susceptibility mapping on a global scale using the method of logistic regression

Lin

Wang

2017

Nat. Hazards Earth Syst. Sci.

117

View full text Add to dashboard Cite

show abstract

“…Moreover, before building the model, the procedure developed for the individuation of the most important predictor variables improved the knowledge about mechanisms which regulate the location of the damaged roads in such an area, avoiding collinearity and bias that could reduce the reliability of the susceptibility estimation (Farrar and Glauber, 1967;Hosmer and Lemeshow, 1990;Bai et al, 2010). The robustness of the proposed methodology was also confirmed by the low confidence degree of AUCs measured for the created models (Petschko et al, 2014).…”

Section: Discussionmentioning

confidence: 96%

Estimation of the susceptibility of a road network to shallow landslides with the integration of the sediment connectivity

Bordoni

Persichillo

Meisina

et al. 2018

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Landslides cause severe damage to the road network of the hit zone, in terms of both direct (partial or complete destruction of a road or blockages) and indirect (traffic restriction or the cut-off of a certain area) costs. Thus, the identification of the parts of the road network that are more susceptible to landslides is fundamental to reduce the risk to the population potentially exposed and the financial expense caused by the damage. For these reasons, this paper aimed to develop and test a data-driven model for the identification of road sectors that are susceptible to being hit by shallow landslides triggered in slopes upstream from the infrastructure. This model was based on the Generalized Additive Method, where the function relating predictors and response variable is an empirically fitted smooth function that allows fitting the data in the more likely functional form, considering also non-linear relations. This work also analyzed the importance, on the estimation of the susceptibility, of considering or not the sediment connectivity, which influences the path and the travel distance of the materials mobilized by a slope failure until hitting a potential barrier such as a road. The study was carried out in a catchment of northeastern Oltrepò Pavese (northern Italy), where several shallow landslides affected roads in the last 8 years. The most significant explanatory variables were selected by a random partition of the available dataset in two parts (training and test subsets), 100 times according to a bootstrap procedure. These variables (selected 80 times by the bootstrap procedure) were used to build the final susceptibility model, the accuracy of which was estimated through a 100-fold repetition of the holdout method for regression, based on the training and test sets created through the 100 bootstrap model selection. The presented methodology allows the identification, in a robust and reliable way, of the most susceptible road sectors that could be hit by sediments delivered by landslides. The best predictive capability was obtained using a model in which the index of connectivity was also calculated according to a linear relationship, was considered. Most susceptible road traits resulted to be located below steep slopes with a limited height (lower than 50 m), where sediment connectivity is high. Different land use scenarios were considered in order to estimate possible changes in road susceptibility. Land use classes of the study area were characterized by similar connectivity features. As a consequence, variations on the susceptibility of the road network according to different scenarios of distribution of land cover were limited. The results of this research demonstrate the ability of the developed methodology in the assessment of susceptible roads. This could give the managers of infrastructure information about the criticality of the different road traits, thereby allowing attention and economic budgets to be shifted towards the most critical assets, where structural and non-structur...

show abstract

“…Esta función tiene una forma sigmoidal que puede ser interpretada como de susceptibilidad mínima de un área a sufrir deslizamientos cuando la función tiene valores bajos y ésta se mantiene como de baja susceptibilidad hasta que cierto umbral es alcanzado, entonces la probabilidad de deslizamientos aumenta rápidamente conforme los valores de la función se incrementan (Kleinbaum y Klein, 2002). Ambos modelos definen bien las zonas que intuitivamente parecen ser susceptibles a deslizamientos (Morrissey et al, 2001;Ohlmacher y Davis, 2003;Yesilnacar y Topal, 2005;Can et al, 2005;Ayalew y Yamagishi, 2005;Meisina y Scarabelli, 2007;Deb y El-Kadi, 2009;Bai et al, 2010;Van Den Eeckhaunt et al, 2005). Estos dos modelos fueron adaptados en el sistema, LOGISNET, mediante el uso de Arc Macro Language (AML) en el SIG ArcInfo.…”

Section: Antecedentesunclassified

Inventario multitemporal, análisis de susceptibilidad y estimación de volumen de deslizamientos en el flanco SW del volcán Pico de Orizaba, Puebla-Veracruz

Paulín

Bursik

Pouget

et al. 2014

BSGM

View full text Add to dashboard Cite

Inventario multitemporal, análisis de susceptibilidad y estimación de volumen de deslizamientos 343 ResumenEste artículo provee un panorama general de la investigación en curso del Instituto de Geografía de la UNAM, que busca crear una metodología integral para el desarrollo de cartografía de inventarios multitemporales, de susceptibilidad y estimación de volúmenes de deslizamientos mediante el uso de Sistemas de Información Geográfica (SIG). La metodología se establece para terrenos volcáni-cos, donde deslizamientos superficiales y flujos de escombros son frecuentes a lo largo de las laderas y los sistemas fluviales de los volcanes. La cuenca del Río Chiquito-Barranca del Muerto en el flanco suroeste del volcán Pico de Orizaba se ha seleccionado como caso de estudio para caracterizar las áreas que son propensas a la inestabilidad de las laderas en terrenos volcánicos. La ocurrencia de deslizamientos se determinó a través de un inventario de deslizamientos creado a partir de fotos aéreas multitemporales y trabajo de campo. En este estudio se modela (simula) la susceptibilidad a deslizamientos usando un modelo cartográfico-hidrológico (Stability Index MAPping (SINMAP)) y un modelo estadístico (Regresión Logística Múltiple (RLM)). Ambos modelos están integrados dentro de la aplicación LOGISNET (desarrollado mediante el uso de macros (AML) del sistema de información geográfica (SIG) ArcInfo Workstation. Su implementación mostró que ambos modelos poseen un grado moderado de concordancia con el inventario de deslizamientos, prefiriéndose la RLM para futuros análisis por su flexibilidad de incluir otras variables. Para la estimación de volúmenes de materiales aportados por los deslizamientos a los cauces, se seleccionaron los deslizamientos superficiales. El área y volumen de deslizamientos superficiales individuales fueron obtenidos en campo y a través de la base de datos del inventario de deslizamientos, para establecer una relación empírica: área-volumen. La relación se utilizó para el uso de una ley de potencias con la que se estimó el volumen total de deslizamientos de tierra en el área de estudio. Los resultados son importantes para comprender la evolución a largo plazo del sistema fluvial en el flanco suroeste del volcán Pico de Orizaba, y apoyar el desarrollo de una metodología útil para la elaboración de inventarios, el análisis de la susceptibilidad y estimación de volúmenes de deslizamientos en terrenos volcánicos.

show abstract

GIS-based logistic regression for landslide susceptibility mapping of the Zhongxian segment in the Three Gorges area, China

Cited by 432 publications

References 33 publications

Landslide susceptibility mapping on a global scale using the method of logistic regression

Landslide susceptibility mapping on a global scale using the method of logistic regression

Estimation of the susceptibility of a road network to shallow landslides with the integration of the sediment connectivity

Inventario multitemporal, análisis de susceptibilidad y estimación de volumen de deslizamientos en el flanco SW del volcán Pico de Orizaba, Puebla-Veracruz

Contact Info

Product

Resources

About