A Geographically Weighted Total Composite Error Analysis for Soft Classification

Narumasa Tsutsumida, Takahiro Yoshida, Daisuke Murakami, Tomoki Nakaya

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Errors in land cover classification are often spatially heterogeneous even though a soft classification model such as spectral unmixing is implemented to mitigate a mixed pixel problem. The estimated land covers are fractions of targeted classes with the restriction of the sum to one and being non-negative. To assess the classification with considering a spatial heterogeneity, we propose a geographically weighted total composite error analysis. By using the USGS global reference database, we assessed errors of spectral unmixing classification of ALOS AVNIR-2 data into 4 land cover classes. Results yield a spatial surface of local errors by the Aitchison distance and address that the error magnitude across space is associated with the complexity of land covers.

Original languageEnglish
Title of host publication2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages874-876
Number of pages3
ISBN (Electronic)9781728163741
DOIs
Publication statusPublished - 2020 Sept 26
Event2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Virtual, Waikoloa, United States
Duration: 2020 Sept 262020 Oct 2

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Country/TerritoryUnited States
CityVirtual, Waikoloa
Period20/9/2620/10/2

Keywords

  • Error assessment
  • soft classification
  • spatial compositional data
  • spatial heterogeneity
  • validation

Fingerprint

Dive into the research topics of 'A Geographically Weighted Total Composite Error Analysis for Soft Classification'. Together they form a unique fingerprint.

Cite this