Species-level classification of mangrove forest using AVIRIS-NG hyperspectral imagery
Species-level classification of mangrove forest using AVIRIS-NG hyperspectral imagery
Species-level classification of mangroves provides important inputs for conservation, rehabilitation and understanding of ecosystem functions. The hyperspectral sensor, Airborne Visible InfraRed Imaging Spectrometer-New Generation (AVIRIS-NG), holds promises for species-level discrimination by virtue of its coverage across a wider spectrum at very high spatial resolution. Using the continuum removal (CR) technique and absorption band depth (ABD), this study applied Random Forest (RF) model to classify the distribution of three species (Heritiera fomes, Excoecaria agallocha and Avicennia officinalis) and two of their combinations (Heritiera fomes-Excoecaria agallocha and Avicennia officinalis-Excoecaria agallocha). The classified map demonstrated good accuracy (overall accuracy = 88%; kappa coefficient = 0.84) using ABD as an independent variable. The important wavelengths (972, 1172, 1177 nm) identified for mangrove species discrimination correspond to water absorption bands. This characteristic may be replicated for species-level classification of other mangrove forests with similar species.
Bhitarkanika Wildlife Sanctuary, Random Forest, absorption band depth, continuum removal, spectral signature
522-533
Paramanik, Somnath
8fb0a9ec-ddf2-4ceb-a749-131a401c3753
Deep, Nikhil Raj
cad92491-2813-46c3-ae73-e015bbf5f667
Behera, Mukunda Dev
6e4169d4-2c20-422c-b2c2-1a15dc41e29d
Bhattacharya, Bimal Kumar
219bdfd9-5b55-46b7-9f5e-7bf19a6d7d59
Dash, Jadunandan
51468afb-3d56-4d3a-aace-736b63e9fac8
25 May 2023
Paramanik, Somnath
8fb0a9ec-ddf2-4ceb-a749-131a401c3753
Deep, Nikhil Raj
cad92491-2813-46c3-ae73-e015bbf5f667
Behera, Mukunda Dev
6e4169d4-2c20-422c-b2c2-1a15dc41e29d
Bhattacharya, Bimal Kumar
219bdfd9-5b55-46b7-9f5e-7bf19a6d7d59
Dash, Jadunandan
51468afb-3d56-4d3a-aace-736b63e9fac8
Paramanik, Somnath, Deep, Nikhil Raj, Behera, Mukunda Dev, Bhattacharya, Bimal Kumar and Dash, Jadunandan
(2023)
Species-level classification of mangrove forest using AVIRIS-NG hyperspectral imagery.
Remote Sensing Letters, 14 (5), .
(doi:10.1080/2150704X.2023.2215945).
Abstract
Species-level classification of mangroves provides important inputs for conservation, rehabilitation and understanding of ecosystem functions. The hyperspectral sensor, Airborne Visible InfraRed Imaging Spectrometer-New Generation (AVIRIS-NG), holds promises for species-level discrimination by virtue of its coverage across a wider spectrum at very high spatial resolution. Using the continuum removal (CR) technique and absorption band depth (ABD), this study applied Random Forest (RF) model to classify the distribution of three species (Heritiera fomes, Excoecaria agallocha and Avicennia officinalis) and two of their combinations (Heritiera fomes-Excoecaria agallocha and Avicennia officinalis-Excoecaria agallocha). The classified map demonstrated good accuracy (overall accuracy = 88%; kappa coefficient = 0.84) using ABD as an independent variable. The important wavelengths (972, 1172, 1177 nm) identified for mangrove species discrimination correspond to water absorption bands. This characteristic may be replicated for species-level classification of other mangrove forests with similar species.
Text
ABD_Mangrove_Hyp_Sp_Cls_RSL_R1
- Accepted Manuscript
More information
Accepted/In Press date: 7 May 2023
Published date: 25 May 2023
Additional Information:
Funding Information:
All Authors are thankful to the authorities of CORAL and IIT Kharagpur for providing research facilities. The authors are thankful to the Odisha State Forest and Wildlife Department for permission for the field visit. The authors are also thankful to SAC and ISRO for providing the AVIRIS-NG dataset. We thank anonymous reviewers for providing valuable feedback to its earlier version, which has improved the manuscript to a great extent.
Keywords:
Bhitarkanika Wildlife Sanctuary, Random Forest, absorption band depth, continuum removal, spectral signature
Identifiers
Local EPrints ID: 478283
URI: http://eprints.soton.ac.uk/id/eprint/478283
ISSN: 2150-704X
PURE UUID: 7d306c2d-857e-48f7-b18b-d4397bf9fc29
Catalogue record
Date deposited: 27 Jun 2023 17:08
Last modified: 12 Nov 2024 05:08
Export record
Altmetrics
Contributors
Author:
Somnath Paramanik
Author:
Nikhil Raj Deep
Author:
Mukunda Dev Behera
Author:
Bimal Kumar Bhattacharya
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics