A transferability study of the kernel-based reclassification algorithm for habitat delineation

I. Keramitsoglou, D. Stratoulias, E. Fitoka, C. Kontoes, N.A. Sifakis

Research output: Contribution to journalArticleAcademicpeer-review

3 Citations (Scopus)

Abstract

Wetland mapping using Earth observation (EO) data has proved to be a challenging task for practitioners due to the complexity in the spatial structure and composition, the wide within-class spectral variability and the absence of easily distinguishable boundaries between habitat types. Furthermore, the inherent temporal water instability of these landscapes poses an obstacle to the integration of field data with remote sensing data, which also are not acquired simultaneously at all times.To cope with these limitations we tested the applicability of the Kernel-based reclassification (KRC) algorithm on very high spatial resolution (VHR) satellite imagery over a wetland. A composite multi-temporal (i.e. dual-date) VHR WorldView-2 image consisting of spectral bands and indices derived from two images acquired during flooded and dry water conditions were employed. This dataset stresses the seasonal variations of the habitat in response to environmental changes (i.e. flooding) occurring between the two acquisition dates. Multi-temporal imagery is an important information source for fine mapping of wetlands such are river deltas. A multi-temporal approach could reveal even more specific information during the phenology of these habitats.The methodology was applied firstly to Axios and then to Aliakmonas river deltas in Northern Greece. The results revealed an overall accuracy of 53% in the first and more complex site, and 86% in the second site
Original languageEnglish
Pages (from-to)38-47
JournalInternational Journal of Applied Earth Observation and Geoinformation (JAG)
Volume37
DOIs
Publication statusPublished - 9 Jan 2015

Fingerprint

Wetlands
wetland
spatial resolution
habitat
Rivers
Satellite imagery
river
habitat type
satellite imagery
phenology
Water
Remote sensing
environmental change
imagery
flooding
seasonal variation
Earth (planet)
remote sensing
water
methodology

Keywords

  • ITC-ISI-JOURNAL-ARTICLE

Cite this

Keramitsoglou, I. ; Stratoulias, D. ; Fitoka, E. ; Kontoes, C. ; Sifakis, N.A. / A transferability study of the kernel-based reclassification algorithm for habitat delineation. In: International Journal of Applied Earth Observation and Geoinformation (JAG). 2015 ; Vol. 37. pp. 38-47.
@article{a95235ae26b54c768e68fb4fdba12406,
title = "A transferability study of the kernel-based reclassification algorithm for habitat delineation",
abstract = "Wetland mapping using Earth observation (EO) data has proved to be a challenging task for practitioners due to the complexity in the spatial structure and composition, the wide within-class spectral variability and the absence of easily distinguishable boundaries between habitat types. Furthermore, the inherent temporal water instability of these landscapes poses an obstacle to the integration of field data with remote sensing data, which also are not acquired simultaneously at all times.To cope with these limitations we tested the applicability of the Kernel-based reclassification (KRC) algorithm on very high spatial resolution (VHR) satellite imagery over a wetland. A composite multi-temporal (i.e. dual-date) VHR WorldView-2 image consisting of spectral bands and indices derived from two images acquired during flooded and dry water conditions were employed. This dataset stresses the seasonal variations of the habitat in response to environmental changes (i.e. flooding) occurring between the two acquisition dates. Multi-temporal imagery is an important information source for fine mapping of wetlands such are river deltas. A multi-temporal approach could reveal even more specific information during the phenology of these habitats.The methodology was applied firstly to Axios and then to Aliakmonas river deltas in Northern Greece. The results revealed an overall accuracy of 53{\%} in the first and more complex site, and 86{\%} in the second site",
keywords = "ITC-ISI-JOURNAL-ARTICLE",
author = "I. Keramitsoglou and D. Stratoulias and E. Fitoka and C. Kontoes and N.A. Sifakis",
year = "2015",
month = "1",
day = "9",
doi = "10.1016/j.jag.2014.11.002",
language = "English",
volume = "37",
pages = "38--47",
journal = "International Journal of Applied Earth Observation and Geoinformation (JAG)",
issn = "1569-8432",
publisher = "Elsevier",

}

A transferability study of the kernel-based reclassification algorithm for habitat delineation. / Keramitsoglou, I.; Stratoulias, D.; Fitoka, E.; Kontoes, C.; Sifakis, N.A.

In: International Journal of Applied Earth Observation and Geoinformation (JAG), Vol. 37, 09.01.2015, p. 38-47.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A transferability study of the kernel-based reclassification algorithm for habitat delineation

AU - Keramitsoglou, I.

AU - Stratoulias, D.

AU - Fitoka, E.

AU - Kontoes, C.

AU - Sifakis, N.A.

PY - 2015/1/9

Y1 - 2015/1/9

N2 - Wetland mapping using Earth observation (EO) data has proved to be a challenging task for practitioners due to the complexity in the spatial structure and composition, the wide within-class spectral variability and the absence of easily distinguishable boundaries between habitat types. Furthermore, the inherent temporal water instability of these landscapes poses an obstacle to the integration of field data with remote sensing data, which also are not acquired simultaneously at all times.To cope with these limitations we tested the applicability of the Kernel-based reclassification (KRC) algorithm on very high spatial resolution (VHR) satellite imagery over a wetland. A composite multi-temporal (i.e. dual-date) VHR WorldView-2 image consisting of spectral bands and indices derived from two images acquired during flooded and dry water conditions were employed. This dataset stresses the seasonal variations of the habitat in response to environmental changes (i.e. flooding) occurring between the two acquisition dates. Multi-temporal imagery is an important information source for fine mapping of wetlands such are river deltas. A multi-temporal approach could reveal even more specific information during the phenology of these habitats.The methodology was applied firstly to Axios and then to Aliakmonas river deltas in Northern Greece. The results revealed an overall accuracy of 53% in the first and more complex site, and 86% in the second site

AB - Wetland mapping using Earth observation (EO) data has proved to be a challenging task for practitioners due to the complexity in the spatial structure and composition, the wide within-class spectral variability and the absence of easily distinguishable boundaries between habitat types. Furthermore, the inherent temporal water instability of these landscapes poses an obstacle to the integration of field data with remote sensing data, which also are not acquired simultaneously at all times.To cope with these limitations we tested the applicability of the Kernel-based reclassification (KRC) algorithm on very high spatial resolution (VHR) satellite imagery over a wetland. A composite multi-temporal (i.e. dual-date) VHR WorldView-2 image consisting of spectral bands and indices derived from two images acquired during flooded and dry water conditions were employed. This dataset stresses the seasonal variations of the habitat in response to environmental changes (i.e. flooding) occurring between the two acquisition dates. Multi-temporal imagery is an important information source for fine mapping of wetlands such are river deltas. A multi-temporal approach could reveal even more specific information during the phenology of these habitats.The methodology was applied firstly to Axios and then to Aliakmonas river deltas in Northern Greece. The results revealed an overall accuracy of 53% in the first and more complex site, and 86% in the second site

KW - ITC-ISI-JOURNAL-ARTICLE

U2 - 10.1016/j.jag.2014.11.002

DO - 10.1016/j.jag.2014.11.002

M3 - Article

VL - 37

SP - 38

EP - 47

JO - International Journal of Applied Earth Observation and Geoinformation (JAG)

JF - International Journal of Applied Earth Observation and Geoinformation (JAG)

SN - 1569-8432

ER -