Technical note: assessing predictive capacity and conditional independence of landslide predisposing factors for shallow landslide susceptibility models

• Autor(a) principal: Pereira, Susana
• Data de Publicação: 2012
• Outros Autores: Zêzere, José, Bateira, Carlos
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Texto Completo: http://hdl.handle.net/10451/37000
• topic: Landslide predisposing factors; Shallow landslide susceptibility models

The aim of this study is to identify the landslide predisposing factors’ combination using a bivariate statistical model that best predicts landslide susceptibility. The best model is one that has simultaneously good performance in terms of suitability and predictive power and has been developed using variables that are conditionally independent. The study area is the Santa Marta de Penaguiao council (70 km ˜ 2 ) located in the Northern Portugal. In order to identify the best combination of landslide predisposing factors, all possible combinations using up to seven predisposing factors were performed, which resulted in 120 predictions that were assessed with a landside inventory containing 767 shallow translational slides. The best landslide susceptibility model was selected according to the model degree of fitness and on the basis of a conditional independence criterion. The best model was developed with only three landslide predisposing factors (slope angle, inverse wetness index, and land use) and was compared with a model developed using all seven landslide predisposing factors. Results showed that it is possible to produce a reliable landslide susceptibility model using fewer landslide predisposing factors, which contributes towards higher conditional independence. 1 Introduction Recent developments in GIS software and increasing computing power allow a substantially high number of independent variables to be used in empirical, data-driven landslide susceptibility models. Recent studies in landslide susceptibility models usually involve over a dozen variables considered as predisposing factors of slope instability (e.g. Lee et al., 2002 (13 variables); Lee and Choi, 2004 (15 variables); van der Eeckhaut et al., 2010 (9 variables); Sterlacchini et al., 2011 (9 variables)). Nevertheless, the evaluation of the weight of each landslide predisposing factor within the predictive model through a thorough sensitivity analysis is frequently missing. In addition, the application of statistic bivariate methods to assess landslide susceptibility assumes conditional independence (CI) of the landslide predisposing factors (Bonham-Carter et al., 1989; Agterberg et al., 1993; Van Westen, 1993; Agterberg and Cheng, 2002; Thiart et al., 2003; Thiery et al., 2007). Blahut et al. (2010) pointed out that spatial probabilities are overestimated when conditional independence is not verified. In this study, the aim is to determine the best combination of landslide predisposing variables using a bivariate statistical model, based on the assessment of goodness of fit and predictive power, using variables that have a high degree of conditional independence. In addition, we assess the number of unique conditions within each landslide susceptibility model associated to each combination of landslide predisposing variables. This number should be minimized when landslide susceptibility maps are made for land use planning and management in order to avoid the over partitioning of the study area.