Landslide susceptibility assessment using SVM machine learning algorithm

Marjanović, Miloš; Kovačević, M.; Bajat, Branislav; Voženílek, Vít

doi:10.1016/j.enggeo.2011.09.006

Cited by 511 publications

(227 citation statements)

References 24 publications

Supporting

Mentioning

192

Contrasting

Unclassified

Order By: Relevance

“…Many studies have illustrated the ability of SVM models to recognize learning patterns, such as nonlinear regression, and obtain the global optimum solutions to these problems (Feng et al, 2004;Marjanović et al, 2011;Micheletti et al, 2011;Hong et al, 2016). Although these problems can be transformed into quadratic convex programming problems, the computation speed of the SVM model is slow when the training data set is large or the dimensionality is high (Zhang et al, 2009).…”

Section: Introductionmentioning

confidence: 99%

Landslide displacement prediction using the GA-LSSVM model and time series analysis: a case study of Three Gorges Reservoir, China

Wen

Tang

Wang

et al. 2017

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Predicting landslide displacement is challenging, but accurate predictions can prevent casualties and economic losses. Many factors can affect the deformation of a landslide, including the geological conditions, rainfall and reservoir water level. Time series analysis was used to decompose the cumulative displacement of landslide into a trend component and a periodic component. Then the least-squares support vector machine (LSSVM) model and genetic algorithm (GA) were used to predict landslide displacement, and we selected a representative landslide with episodic movement deformation as a case study. The trend component displacement, which is associated with the geological conditions, was predicted using a polynomial function, and the periodic component displacement which is associated with external environmental factors, was predicted using the GA-LSSVM model. Furthermore, based on a comparison of the results of the GA-LSSVM model and those of other models, the GA-LSSVM model was superior to other models in predicting landslide displacement, with the smallest root mean square error (RMSE) of 62.4146 mm, mean absolute error (MAE) of 53.0048 mm and mean absolute percentage error (MAPE) of 1.492 % at monitoring station ZG85, while these three values are 87.7215 mm, 74.0601 mm and 1.703 % at ZG86 and 49.0485 mm, 48.5392 mm and 3.131 % at ZG87. The results of the case study suggest that the model can provide good consistency between measured displacement and predicted displacement, and periodic displacement exhibited good agreement with trends in the major influencing factors.

show abstract

Section: Introductionmentioning

confidence: 99%

Landslide displacement prediction using the GA-LSSVM model and time series analysis: a case study of Three Gorges Reservoir, China

Wen

Tang

Wang

et al. 2017

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

show abstract

“…Lee 2005;Goetz et al 2011Goetz et al , 2015Youssef et al 2016;Castro Camilo et al 2017) and Machine-Learning approaches (e.g. Lee et al 2004;Ermini et al 2005;Marjanovic et al 2011;Pham et al 2017) are also used in this type of analyses. Such approaches are very sensitive to the type and quality of the factors chosen for the susceptibility analysis, and the lack of suitable expert opinion can produce unreliable results (Soeters and Van Westen 1996).…”

Section: Introductionmentioning

confidence: 99%

Shallow landslide initiation on terraced slopes: inferences from a physically based approach

Schilirò

Cevasco

Esposito

et al. 2018

Geomatics, Natural Hazards and Risk

View full text Add to dashboard Cite

In the last years, great efforts have been made to improve the assessment of the temporal and spatial occurrence of rainfall-induced shallow landslides. Therefore, in this paper we used a physically based stability model (TRIGRS) in order to reproduce the landslide event occurred in the Monterosso catchment (Cinque Terre, Eastern Liguria, Italy) on 25 October 2011. The input parameters of the numerical model have been evaluated taking into account the land-use setting and paying specific attention to the evaluation of the spatial variation of soil thickness on terraced areas. The resulting safety factor maps have been compared with the inventory map of the landslides triggered during the event. The simulation results, which have been obtained also considering four different spatial resolutions of the digital terrain model, emphasize the influence of land use in shallow landslide occurrence and indicate the importance of a realistic spatial variation of soil thickness to enhance the reliability of the model. Finally, different triggering scenarios have been defined using hourly rainfall values statistically derived from historical data. The results indicate the proneness of the area to shallow landsliding, given that rainfall events with a relatively low return period (e.g. 25 years) can trigger numerous slope failures.

show abstract

“…Moreover, additional four examples representing one topographic and three thematic image maps have been developed (see fig. 2 Based on the practical tasks carried out with all the above introduced examples, it can be stated that all ones are readily applicable in cartographical and geographic practice (as in Marjanovic et al 2011). …”

Section: Discussionmentioning

confidence: 99%

The Cartographic Concept of the Image Map

Voženílek

Bělka²

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Image maps have become very popular and frequently produced cartographical outputs during recent years. However, the unambiguous terminology, definitions, content and appearance specification have not been widely researched. The paper deals with the new definition of image map, its components delineation, and basic classification. The authors understand the image map as a special map portraying geographic space in a particular cartographical projection and map scale, where its content consists of two basic components -image and symbol components. Image component is represented by remote sensing image(s), while symbol component is represented by cartographical symbols. An image map has to have three essential attributes: cartographical projection, map scale and symbol component by means of map language. The authors also present aspects of topographic and thematic image maps.

show abstract

Landslide susceptibility assessment using SVM machine learning algorithm

Cited by 511 publications

References 24 publications

Landslide displacement prediction using the GA-LSSVM model and time series analysis: a case study of Three Gorges Reservoir, China

Landslide displacement prediction using the GA-LSSVM model and time series analysis: a case study of Three Gorges Reservoir, China

Shallow landslide initiation on terraced slopes: inferences from a physically based approach

The Cartographic Concept of the Image Map

Contact Info

Product

Resources

About