Influence of sampling design on landslide susceptibility modeling in lithologically heterogeneous areas

Abstract

This work aims at evaluating the sensitivity of landslide susceptibility mapping (LSM) to sampling design in lithologically-heterogeneous areas. We hypothesize that random sampling of the landslide absence data in such areas can be biased by statistical aggregation of the explanatory variables, which impact the model outputs. To test this hypothesis, we train a Random Forest (RF) model in two different domains, as follows: (1) in lithologically heterogeneous areas, and (2) in lithologically homogeneous domains of the respective areas. Two heterogeneous areas are selected in Japan (125 km2) and Romania (497 km2), based on existing landslide inventories that include 371 and 577 scarps, respectively. These areas are divided into two, respectively three domains, defined by lithological units that reflect relatively homogeneous topographies. Fourteen terrain attributes are derived from a 30 m SRTM digital elevation model and employed as explanatory variables. Results show that LSM is sensitive to a random sampling of the absence data in lithologically heterogeneous areas. Accuracy measures improve significantly when sampling and LSM are conducted in lithologically homogeneous domains, as compared to heterogeneous areas, reaching an increase of 9% in AUC and 17% in the Kappa index.

A review on landslide susceptibility mapping research in Bangladesh

“…During non-landslide sampling buffer analysis [ 78 ], Mahalanobis distances [ 79 ] should be considered because the distance of non-landslide location has a significant impact on the accuracy of landslide susceptibility map [ 77 , 78 ]. Non-landslide sampling in environmental and lithological heterogeneous and homogeneous areas also affects the accuracy of statistical models [ 80 ]. So these should be considered during landslide susceptibility mapping in Bangladesh because these are not tested yet.…”

Landslide type inference based on statistical analysis of a high-resolution digital elevation model in Gorce National Park, Poland

“…In the proposed method, we attempted to quantify the geometric features of the landslide using the differences of descriptive statistics of the slope and aspect calculated inside and on the outline of the landslide. The data were sampled similarly to Dou et al 46 and Li et al 47 in a regular grid, as landslide modeling in the Carpathians is sensitive to random sampling 48 .…”

Landslide Susceptibility Analysis on the Vicinity of Bogotá-Villavicencio Road (Eastern Cordillera of the Colombian Andes)

“…Meanwhile, the remaining methods follow a different scheme that starts with obtaining a random sampling of points. Based on previous works [85][86][87][88][89], a total of 5000 points have been obtained with GIS tools (QGIS) in the stable zone (absence of landslides) and 5000 points in each of the differentiated landslide typologies (presence). A table was then created by extracting the values of the different factors' layers at each point or pixel.…”