Mapping landslide susceptibility using data-driven methods

José Luı́s Zêzere

doi:10.1016/j.scitotenv.2017.02.188

Return

Mapping landslide susceptibility using data-driven methods

2017-07-01

248

PRE

DOI：10.1016/j.scitotenv.2017.02.188

Original

Original request for help

Save

Abstract

En 中文

Most epistemic uncertainty within data-driven landslide susceptibility assessment results from errors in landslide inventories, difficulty in identifying and mapping landslide causes and decisions related with the modelling procedure. In this work we evaluate and discuss differences observed on landslide susceptibility maps resulting from: (i) the selection of the statistical method; (ii) the selection of the terrain mapping unit; and (iii) the selection of the feature type to represent landslides in the model (polygon versus point). The work is performed in a single study area (Silveira Basin-18.2 km(2) - Lisbon Region, Portugal) using a unique database of geo-environmental landslide predisposing factors and an inventory of 82 shallow translational slides. The logistic regression, the discriminant analysis and two versions of the information value were used and we conclude that multivariate statistical methods perform better when computed over heterogeneous terrain units and should be selected to assess landslide susceptibility based on slope terrain units, geo-hydrological terrain units or census terrain units. However, evidence was found that the chosen terrain mapping unit can produce greater differences on final susceptibility results than those resulting from the chosen statistical method for modelling. The landslide susceptibility should be assessed over grid cell terrain units whenever the spatial accuracy of landslide inventory is good. In addition, a single point per landslide proved to be efficient to generate accurate landslide susceptibility maps, providing the landslides are of small size, thus minimizing the possible existence of heterogeneities of predisposing factors within the landslide boundary. Although during last years the ROC curves have been preferred to evaluate the susceptibility model's performance, evidence was found that the model with the highest AUC ROC is not necessarily the best landslide susceptibility model, namely when terrain mapping units are heterogeneous in size and reduced in number. (C) 2017 Elsevier B.V. All rights reserved.

Keywords:

Landslide susceptibility

Data-driven methods

Terrain mapping units

Validation

Uncertainty

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.