Automatic mapping of event landslides at basin scale in Taiwan using a Montecarlo approach and synthetic land cover fingerprints

Alessandro C. Mondini, Kang Tsung Chang, Shou Hao Chiang, Romy Schlögel, Claudia Notarnicola, Hitoshi Saito

Research output: Contribution to journalArticlepeer-review

15 Scopus citations

Abstract

We propose a framework to systematically generate event landslide inventory maps from satellite images in southern Taiwan, where landslides are frequent and abundant. The spectral information is used to assess the pixel land cover class membership probability through a Maximum Likelihood classifier trained with randomly generated synthetic land cover spectral fingerprints, which are obtained from an independent training images dataset. Pixels are classified as landslides when the calculated landslide class membership probability, weighted by a susceptibility model, is higher than membership probabilities of other classes. We generated synthetic fingerprints from two FORMOSAT-2 images acquired in 2009 and tested the procedure on two other images, one in 2005 and the other in 2009. We also obtained two landslide maps through manual interpretation. The agreement between the two sets of inventories is given by the Cohen's k coefficients of 0.62 and 0.64, respectively. This procedure can now classify a new FORMOSAT-2 image automatically facilitating the production of landslide inventory maps.

Original languageEnglish
Pages (from-to)112-121
Number of pages10
JournalInternational Journal of Applied Earth Observation and Geoinformation
Volume63
DOIs
StatePublished - 2017

Keywords

  • Image analysis
  • Systematic event landslide mapping
  • Uncertainty estimation

Fingerprint

Dive into the research topics of 'Automatic mapping of event landslides at basin scale in Taiwan using a Montecarlo approach and synthetic land cover fingerprints'. Together they form a unique fingerprint.

Cite this