Spectral matching based on discrete particle swarm optimization: A new method for terrestrial water body extraction using multi-temporal Landsat 8 images

Kai Jia, Weiguo Jiang, Jing Li, Zhenghong Tang

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Terrestrial water, an important indicator of inland hydrological status, is sensitive to land use cover change, natural disaster and climate change. An accurate and robust water extraction method can determine the surface water distribution. In this paper, a new method, called the spectrum matching based on discrete particle swarm optimization (SMDPSO) is proposed to recognize water and nonwater in Landsat 8 Operational Land Imager (OLI) images. Only two parameters, the standard water spectrum and the tile size, are considered. These parameters are sufficiently stable so it is unnecessary to change their values for different conditions. By contrast, in supervised methods, samples are chosen based on conditions. Eight test sites covering various water types in different climate conditions are used to assess the performance relative to that of unsupervised and supervised methods in terms of overall accuracy (OA), kappa coefficients (KC), commission error (CE) and omission error (OE). The results show that: (1) SMDPSO achieves the highest accuracy and robustness; (2) SMDPSO has lower OE but higher CE than the supervised method, which means that SMDPSO is the least likely to misclassify water as nonwater, but is more likely to misclassify nonwater as water; (3) SMDPSO has advantages with respect to removing shallows and dark vegetation and preserving the real distribution of small ponds, but cannot recognize shadows, ice, or clouds without the help of other data such as DEM. In addition, a case of flooding in northeastern China is analyzed to demonstrate the applicability of SMDPSO in water inundation mapping. The findings of this study demonstrate a novel robust, low-cost water extraction method that satisfies the requirements of terrestrial water inundation mapping and management.

Original languageEnglish (US)
Pages (from-to)1-18
Number of pages18
JournalRemote Sensing of Environment
Volume209
DOIs
StatePublished - May 2018

Fingerprint

swarms
Landsat
Particle swarm optimization (PSO)
body water
Water
water
extraction method
methodology
method
water body
particle
natural disaster
climate conditions
tiles
digital elevation model
disasters
Ponds
water distribution
Tile
Surface waters

Keywords

  • Discrete particle swarm optimization (DPSO)
  • Flood inundation mapping
  • Landsat 8 Operational Land Imager (OLI)
  • Surface water extraction

ASJC Scopus subject areas

  • Soil Science
  • Geology
  • Computers in Earth Sciences

Cite this

@article{68cc440ec30a403eb8b15c615cbb7bd3,
title = "Spectral matching based on discrete particle swarm optimization: A new method for terrestrial water body extraction using multi-temporal Landsat 8 images",
abstract = "Terrestrial water, an important indicator of inland hydrological status, is sensitive to land use cover change, natural disaster and climate change. An accurate and robust water extraction method can determine the surface water distribution. In this paper, a new method, called the spectrum matching based on discrete particle swarm optimization (SMDPSO) is proposed to recognize water and nonwater in Landsat 8 Operational Land Imager (OLI) images. Only two parameters, the standard water spectrum and the tile size, are considered. These parameters are sufficiently stable so it is unnecessary to change their values for different conditions. By contrast, in supervised methods, samples are chosen based on conditions. Eight test sites covering various water types in different climate conditions are used to assess the performance relative to that of unsupervised and supervised methods in terms of overall accuracy (OA), kappa coefficients (KC), commission error (CE) and omission error (OE). The results show that: (1) SMDPSO achieves the highest accuracy and robustness; (2) SMDPSO has lower OE but higher CE than the supervised method, which means that SMDPSO is the least likely to misclassify water as nonwater, but is more likely to misclassify nonwater as water; (3) SMDPSO has advantages with respect to removing shallows and dark vegetation and preserving the real distribution of small ponds, but cannot recognize shadows, ice, or clouds without the help of other data such as DEM. In addition, a case of flooding in northeastern China is analyzed to demonstrate the applicability of SMDPSO in water inundation mapping. The findings of this study demonstrate a novel robust, low-cost water extraction method that satisfies the requirements of terrestrial water inundation mapping and management.",
keywords = "Discrete particle swarm optimization (DPSO), Flood inundation mapping, Landsat 8 Operational Land Imager (OLI), Surface water extraction",
author = "Kai Jia and Weiguo Jiang and Jing Li and Zhenghong Tang",
year = "2018",
month = "5",
doi = "10.1016/j.rse.2018.02.012",
language = "English (US)",
volume = "209",
pages = "1--18",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Spectral matching based on discrete particle swarm optimization

T2 - A new method for terrestrial water body extraction using multi-temporal Landsat 8 images

AU - Jia, Kai

AU - Jiang, Weiguo

AU - Li, Jing

AU - Tang, Zhenghong

PY - 2018/5

Y1 - 2018/5

N2 - Terrestrial water, an important indicator of inland hydrological status, is sensitive to land use cover change, natural disaster and climate change. An accurate and robust water extraction method can determine the surface water distribution. In this paper, a new method, called the spectrum matching based on discrete particle swarm optimization (SMDPSO) is proposed to recognize water and nonwater in Landsat 8 Operational Land Imager (OLI) images. Only two parameters, the standard water spectrum and the tile size, are considered. These parameters are sufficiently stable so it is unnecessary to change their values for different conditions. By contrast, in supervised methods, samples are chosen based on conditions. Eight test sites covering various water types in different climate conditions are used to assess the performance relative to that of unsupervised and supervised methods in terms of overall accuracy (OA), kappa coefficients (KC), commission error (CE) and omission error (OE). The results show that: (1) SMDPSO achieves the highest accuracy and robustness; (2) SMDPSO has lower OE but higher CE than the supervised method, which means that SMDPSO is the least likely to misclassify water as nonwater, but is more likely to misclassify nonwater as water; (3) SMDPSO has advantages with respect to removing shallows and dark vegetation and preserving the real distribution of small ponds, but cannot recognize shadows, ice, or clouds without the help of other data such as DEM. In addition, a case of flooding in northeastern China is analyzed to demonstrate the applicability of SMDPSO in water inundation mapping. The findings of this study demonstrate a novel robust, low-cost water extraction method that satisfies the requirements of terrestrial water inundation mapping and management.

AB - Terrestrial water, an important indicator of inland hydrological status, is sensitive to land use cover change, natural disaster and climate change. An accurate and robust water extraction method can determine the surface water distribution. In this paper, a new method, called the spectrum matching based on discrete particle swarm optimization (SMDPSO) is proposed to recognize water and nonwater in Landsat 8 Operational Land Imager (OLI) images. Only two parameters, the standard water spectrum and the tile size, are considered. These parameters are sufficiently stable so it is unnecessary to change their values for different conditions. By contrast, in supervised methods, samples are chosen based on conditions. Eight test sites covering various water types in different climate conditions are used to assess the performance relative to that of unsupervised and supervised methods in terms of overall accuracy (OA), kappa coefficients (KC), commission error (CE) and omission error (OE). The results show that: (1) SMDPSO achieves the highest accuracy and robustness; (2) SMDPSO has lower OE but higher CE than the supervised method, which means that SMDPSO is the least likely to misclassify water as nonwater, but is more likely to misclassify nonwater as water; (3) SMDPSO has advantages with respect to removing shallows and dark vegetation and preserving the real distribution of small ponds, but cannot recognize shadows, ice, or clouds without the help of other data such as DEM. In addition, a case of flooding in northeastern China is analyzed to demonstrate the applicability of SMDPSO in water inundation mapping. The findings of this study demonstrate a novel robust, low-cost water extraction method that satisfies the requirements of terrestrial water inundation mapping and management.

KW - Discrete particle swarm optimization (DPSO)

KW - Flood inundation mapping

KW - Landsat 8 Operational Land Imager (OLI)

KW - Surface water extraction

UR - http://www.scopus.com/inward/record.url?scp=85042356797&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042356797&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2018.02.012

DO - 10.1016/j.rse.2018.02.012

M3 - Article

AN - SCOPUS:85042356797

VL - 209

SP - 1

EP - 18

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

ER -