SciELO - Scientific Electronic Library Online

 
vol.22 número46Parameters for açaí pulp freezingPhotovoltaic Potential Estimation by Means of Data Mining in Four Colombian Cities índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

  • Em processo de indexaçãoCitado por Google
  • Não possue artigos similaresSimilares em SciELO
  • Em processo de indexaçãoSimilares em Google

Compartilhar


TecnoLógicas

versão impressa ISSN 0123-7799versão On-line ISSN 2256-5337

Resumo

ARISTIZABAL, Edier; VASQUEZ, Mariana  e  RUIZ, Diana. The Susceptibility of Landslide Evaluation and Zoning by Statistical Methods. TecnoL. [online]. 2019, vol.22, n.46, pp.43-64. ISSN 0123-7799.  https://doi.org/10.22430/22565337.1247.

Evaluating and zoning mass movement landslide is a fundamental tool for land planning. There are different methods that help to establish in a regional scale landslide hazard. The most common methods are bivariate statistics and multivariate statistic, which need a landslide historical inventory. This study takes a place in the North of the Andes in a region of Colombia called Aburrá Valley, for evaluating and zoning landslide susceptibility by two methods, one of them is bivariate statistics called Weights of Evidence which is recommended by the Geological Service of Colombia for rural area, and the second one is a multivariate statistic method, called logistic regression, which is widely used worldwide. Both methods are supported in frequency histogram, Pearson correlation, Discriminant Analysis, and Principal Component Analysis. The accuracy of the landslide susceptibility maps produced from the two models is classified in high, medium and low by ROC analysis. The AUC plot estimation results showed that the susceptibility map using Logistic regression has a training accuracy of 76.5% and a prediction capacity of 77.5 %. The Weights of evidence method has the highest training accuracy of 77.8 % and a prediction of 77.5 %. This result allows to include the methods in territorial planning studies.

Palavras-chave : Weight of Evidence; logistic regression; hazard; mass movements; Valle de Aburrá.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )