Salt marsh elevation and habitat mapping using hyperspectral and LIDAR data

Christine Hladik, John Schalles, Merryl Alber

Research output: Contribution to journalArticle

64 Citations (Scopus)

Abstract

Accurate mapping of both elevation and plant distributions in salt marshes is important for management and conservation goals. Although light detection and ranging (LIDAR) is effective at measuring surface elevations, laser penetration is limited in dense salt marsh vegetation. In a previous study, we found that LIDAR-derived digital elevation model (DEM) error varied with vegetation cover. We derived cover-class-specific correction factors to reduce these errors, including separate corrections for three different height classes of Spartina alterniflora, the dominant macrophyte in southeastern U.S. salt marshes. In order to apply these cover class-specific corrections, it is necessary to have information on the distribution of cover classes in a LIDAR-derived DEM. Hyperspectral imagery has been shown to be suitable for the separation of salt marsh vegetation species by spectral signatures, and can be used to determine cover classes; however, there is persistent confusion both among the different height classes of S. alterniflora and between plants and mud (the Spartina problem). This paper presents a method to overcome the respective limitations of LIDAR and hyperspectral imagery through the use of multisensor data. An initial classification of hyperspectral imagery based on the maximum likelihood classification algorithm was used in a decision tree in combination with elevation and normalized difference vegetation index (NDVI) derived from the hyperspectral imagery to map nine salt marsh cover classes. The decision tree appreciably reduced the Spartina problem by reassigning classes using these ancillary data and resulted in a final overall classification accuracy of 90%, with a quantity disagreement of 1% and an allocation disagreement of 9%. The resulting hyperspectral image classification was then used as the basis for applying cover class-specific elevation correction factors to the LIDAR-derived DEM. Applying these correction factors greatly improved the accuracy of the DEM: overall mean error decreased from 0.10. ±. 0.12 (SD) to - 0.003. ±. 0.10. m, and root mean squared error from 0.15 to 0.10. m. Our results suggest that the use of decision trees to combine elevation and spectral information can aid both hyperspectral image classification and DEM elevation mapping.

Original languageEnglish
Pages (from-to)318-330
Number of pages13
JournalRemote Sensing of Environment
Volume139
DOIs
StatePublished - Dec 2013

Fingerprint

hyperspectral imagery
lidar
salt marshes
digital elevation models
saltmarsh
digital elevation model
Salts
Decision trees
taxonomy
habitat
imagery
habitats
Image classification
Spartina
Spartina alterniflora
image classification
vegetation
Maximum likelihood
Conservation
macrophyte

All Science Journal Classification (ASJC) codes

  • Computers in Earth Sciences
  • Soil Science
  • Geology

Cite this

Salt marsh elevation and habitat mapping using hyperspectral and LIDAR data. / Hladik, Christine; Schalles, John; Alber, Merryl.

In: Remote Sensing of Environment, Vol. 139, 12.2013, p. 318-330.

Research output: Contribution to journalArticle

@article{4b7acf2717164e94b84b9cc4a04c9c2d,
title = "Salt marsh elevation and habitat mapping using hyperspectral and LIDAR data",
abstract = "Accurate mapping of both elevation and plant distributions in salt marshes is important for management and conservation goals. Although light detection and ranging (LIDAR) is effective at measuring surface elevations, laser penetration is limited in dense salt marsh vegetation. In a previous study, we found that LIDAR-derived digital elevation model (DEM) error varied with vegetation cover. We derived cover-class-specific correction factors to reduce these errors, including separate corrections for three different height classes of Spartina alterniflora, the dominant macrophyte in southeastern U.S. salt marshes. In order to apply these cover class-specific corrections, it is necessary to have information on the distribution of cover classes in a LIDAR-derived DEM. Hyperspectral imagery has been shown to be suitable for the separation of salt marsh vegetation species by spectral signatures, and can be used to determine cover classes; however, there is persistent confusion both among the different height classes of S. alterniflora and between plants and mud (the Spartina problem). This paper presents a method to overcome the respective limitations of LIDAR and hyperspectral imagery through the use of multisensor data. An initial classification of hyperspectral imagery based on the maximum likelihood classification algorithm was used in a decision tree in combination with elevation and normalized difference vegetation index (NDVI) derived from the hyperspectral imagery to map nine salt marsh cover classes. The decision tree appreciably reduced the Spartina problem by reassigning classes using these ancillary data and resulted in a final overall classification accuracy of 90{\%}, with a quantity disagreement of 1{\%} and an allocation disagreement of 9{\%}. The resulting hyperspectral image classification was then used as the basis for applying cover class-specific elevation correction factors to the LIDAR-derived DEM. Applying these correction factors greatly improved the accuracy of the DEM: overall mean error decreased from 0.10. ±. 0.12 (SD) to - 0.003. ±. 0.10. m, and root mean squared error from 0.15 to 0.10. m. Our results suggest that the use of decision trees to combine elevation and spectral information can aid both hyperspectral image classification and DEM elevation mapping.",
author = "Christine Hladik and John Schalles and Merryl Alber",
year = "2013",
month = "12",
doi = "10.1016/j.rse.2013.08.003",
language = "English",
volume = "139",
pages = "318--330",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Salt marsh elevation and habitat mapping using hyperspectral and LIDAR data

AU - Hladik, Christine

AU - Schalles, John

AU - Alber, Merryl

PY - 2013/12

Y1 - 2013/12

N2 - Accurate mapping of both elevation and plant distributions in salt marshes is important for management and conservation goals. Although light detection and ranging (LIDAR) is effective at measuring surface elevations, laser penetration is limited in dense salt marsh vegetation. In a previous study, we found that LIDAR-derived digital elevation model (DEM) error varied with vegetation cover. We derived cover-class-specific correction factors to reduce these errors, including separate corrections for three different height classes of Spartina alterniflora, the dominant macrophyte in southeastern U.S. salt marshes. In order to apply these cover class-specific corrections, it is necessary to have information on the distribution of cover classes in a LIDAR-derived DEM. Hyperspectral imagery has been shown to be suitable for the separation of salt marsh vegetation species by spectral signatures, and can be used to determine cover classes; however, there is persistent confusion both among the different height classes of S. alterniflora and between plants and mud (the Spartina problem). This paper presents a method to overcome the respective limitations of LIDAR and hyperspectral imagery through the use of multisensor data. An initial classification of hyperspectral imagery based on the maximum likelihood classification algorithm was used in a decision tree in combination with elevation and normalized difference vegetation index (NDVI) derived from the hyperspectral imagery to map nine salt marsh cover classes. The decision tree appreciably reduced the Spartina problem by reassigning classes using these ancillary data and resulted in a final overall classification accuracy of 90%, with a quantity disagreement of 1% and an allocation disagreement of 9%. The resulting hyperspectral image classification was then used as the basis for applying cover class-specific elevation correction factors to the LIDAR-derived DEM. Applying these correction factors greatly improved the accuracy of the DEM: overall mean error decreased from 0.10. ±. 0.12 (SD) to - 0.003. ±. 0.10. m, and root mean squared error from 0.15 to 0.10. m. Our results suggest that the use of decision trees to combine elevation and spectral information can aid both hyperspectral image classification and DEM elevation mapping.

AB - Accurate mapping of both elevation and plant distributions in salt marshes is important for management and conservation goals. Although light detection and ranging (LIDAR) is effective at measuring surface elevations, laser penetration is limited in dense salt marsh vegetation. In a previous study, we found that LIDAR-derived digital elevation model (DEM) error varied with vegetation cover. We derived cover-class-specific correction factors to reduce these errors, including separate corrections for three different height classes of Spartina alterniflora, the dominant macrophyte in southeastern U.S. salt marshes. In order to apply these cover class-specific corrections, it is necessary to have information on the distribution of cover classes in a LIDAR-derived DEM. Hyperspectral imagery has been shown to be suitable for the separation of salt marsh vegetation species by spectral signatures, and can be used to determine cover classes; however, there is persistent confusion both among the different height classes of S. alterniflora and between plants and mud (the Spartina problem). This paper presents a method to overcome the respective limitations of LIDAR and hyperspectral imagery through the use of multisensor data. An initial classification of hyperspectral imagery based on the maximum likelihood classification algorithm was used in a decision tree in combination with elevation and normalized difference vegetation index (NDVI) derived from the hyperspectral imagery to map nine salt marsh cover classes. The decision tree appreciably reduced the Spartina problem by reassigning classes using these ancillary data and resulted in a final overall classification accuracy of 90%, with a quantity disagreement of 1% and an allocation disagreement of 9%. The resulting hyperspectral image classification was then used as the basis for applying cover class-specific elevation correction factors to the LIDAR-derived DEM. Applying these correction factors greatly improved the accuracy of the DEM: overall mean error decreased from 0.10. ±. 0.12 (SD) to - 0.003. ±. 0.10. m, and root mean squared error from 0.15 to 0.10. m. Our results suggest that the use of decision trees to combine elevation and spectral information can aid both hyperspectral image classification and DEM elevation mapping.

UR - http://www.scopus.com/inward/record.url?scp=84883756068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883756068&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2013.08.003

DO - 10.1016/j.rse.2013.08.003

M3 - Article

VL - 139

SP - 318

EP - 330

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

ER -