Analysis of the temporal and spatial controlling factors in affecting the accuracy of landslide predicting model at Taiwan

Teng To Yu, Youg Sin Cheng, Wen Fei Peng, Pei Lin Lee

Research output: Contribution to journalConference article

Abstract

Most of the landslides are triggered by rainfall, earthquake or the joint effect from both. Landslide inventory map by GIS via remote sensing offer the spatial distribution of it across certain external event. The landslide model thus been trained to link the occurrence and non-occurrence of individual mass wasting on top of proposing factors/layers. Chosen factors with various calculated weighting values becomes as the base of predicting the region and condition for future landslide called as Landslide Susceptibility Mapping (LSM). It is found that the temporal factor has less AUC values than spatial factors at Taiwan, after examining the 20 years catalog and thousand cases of landslide island wide. Different resolution of DEM and NDVI from satellite image, hyper spectrum and LiDAR are utilized to resolve the degree of impact of it. The require accuracy and resolution of base map is directly link to the accuracy and also minimum mapping size of catalog, and the non-linear relationship of external factors still cannot be well predicted by the training model. To achieve better accuracy of LSM the temporal and non-linearity properties should be addressed, especially under the influence of global warming.

Original languageEnglish
Pages (from-to)579-582
Number of pages4
JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Volume42
Issue number3W4
DOIs
Publication statusPublished - 2018 Mar 6
Event2018 Geoinformation for Disaster Management Conference, Gi4DM 2018 - Istanbul, Turkey
Duration: 2018 Mar 182018 Mar 21

Fingerprint

Landslides
landslide
Taiwan
weighting
Values
Geographical Information System
natural disaster
event
mass wasting
Global warming
analysis
NDVI
nonlinearity
Geographic information systems
Spatial distribution
digital elevation model
Rain
Remote sensing
global warming
Earthquakes

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Geography, Planning and Development

Cite this

@article{061995cd10c2422cb6970f6ff1c7d1b7,
title = "Analysis of the temporal and spatial controlling factors in affecting the accuracy of landslide predicting model at Taiwan",
abstract = "Most of the landslides are triggered by rainfall, earthquake or the joint effect from both. Landslide inventory map by GIS via remote sensing offer the spatial distribution of it across certain external event. The landslide model thus been trained to link the occurrence and non-occurrence of individual mass wasting on top of proposing factors/layers. Chosen factors with various calculated weighting values becomes as the base of predicting the region and condition for future landslide called as Landslide Susceptibility Mapping (LSM). It is found that the temporal factor has less AUC values than spatial factors at Taiwan, after examining the 20 years catalog and thousand cases of landslide island wide. Different resolution of DEM and NDVI from satellite image, hyper spectrum and LiDAR are utilized to resolve the degree of impact of it. The require accuracy and resolution of base map is directly link to the accuracy and also minimum mapping size of catalog, and the non-linear relationship of external factors still cannot be well predicted by the training model. To achieve better accuracy of LSM the temporal and non-linearity properties should be addressed, especially under the influence of global warming.",
author = "Yu, {Teng To} and Cheng, {Youg Sin} and Peng, {Wen Fei} and Lee, {Pei Lin}",
year = "2018",
month = "3",
day = "6",
doi = "10.5194/isprs-archives-XLII-3-W4-579-2018",
language = "English",
volume = "42",
pages = "579--582",
journal = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
issn = "1682-1750",
number = "3W4",

}

TY - JOUR

T1 - Analysis of the temporal and spatial controlling factors in affecting the accuracy of landslide predicting model at Taiwan

AU - Yu, Teng To

AU - Cheng, Youg Sin

AU - Peng, Wen Fei

AU - Lee, Pei Lin

PY - 2018/3/6

Y1 - 2018/3/6

N2 - Most of the landslides are triggered by rainfall, earthquake or the joint effect from both. Landslide inventory map by GIS via remote sensing offer the spatial distribution of it across certain external event. The landslide model thus been trained to link the occurrence and non-occurrence of individual mass wasting on top of proposing factors/layers. Chosen factors with various calculated weighting values becomes as the base of predicting the region and condition for future landslide called as Landslide Susceptibility Mapping (LSM). It is found that the temporal factor has less AUC values than spatial factors at Taiwan, after examining the 20 years catalog and thousand cases of landslide island wide. Different resolution of DEM and NDVI from satellite image, hyper spectrum and LiDAR are utilized to resolve the degree of impact of it. The require accuracy and resolution of base map is directly link to the accuracy and also minimum mapping size of catalog, and the non-linear relationship of external factors still cannot be well predicted by the training model. To achieve better accuracy of LSM the temporal and non-linearity properties should be addressed, especially under the influence of global warming.

AB - Most of the landslides are triggered by rainfall, earthquake or the joint effect from both. Landslide inventory map by GIS via remote sensing offer the spatial distribution of it across certain external event. The landslide model thus been trained to link the occurrence and non-occurrence of individual mass wasting on top of proposing factors/layers. Chosen factors with various calculated weighting values becomes as the base of predicting the region and condition for future landslide called as Landslide Susceptibility Mapping (LSM). It is found that the temporal factor has less AUC values than spatial factors at Taiwan, after examining the 20 years catalog and thousand cases of landslide island wide. Different resolution of DEM and NDVI from satellite image, hyper spectrum and LiDAR are utilized to resolve the degree of impact of it. The require accuracy and resolution of base map is directly link to the accuracy and also minimum mapping size of catalog, and the non-linear relationship of external factors still cannot be well predicted by the training model. To achieve better accuracy of LSM the temporal and non-linearity properties should be addressed, especially under the influence of global warming.

UR - http://www.scopus.com/inward/record.url?scp=85044519620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044519620&partnerID=8YFLogxK

U2 - 10.5194/isprs-archives-XLII-3-W4-579-2018

DO - 10.5194/isprs-archives-XLII-3-W4-579-2018

M3 - Conference article

AN - SCOPUS:85044519620

VL - 42

SP - 579

EP - 582

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

IS - 3W4

ER -