Joint Characterization of the Cryospheric Spectral Feature Space
Multispectral and hyperspectral feature spaces are useful for a variety of remote sensing applications ranging from spectral mixture modeling to discrete thematic classification. In many of these applications, models are used to project the higher dimensional continuum of reflectances (or radiances)...
Published in: | Frontiers in Remote Sensing |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Frontiers Media S.A.
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3389/frsen.2021.793228 https://doaj.org/article/6d521a44116b43e19b51576c4cbd06d5 |
id |
ftdoajarticles:oai:doaj.org/article:6d521a44116b43e19b51576c4cbd06d5 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:6d521a44116b43e19b51576c4cbd06d5 2023-05-15T16:21:32+02:00 Joint Characterization of the Cryospheric Spectral Feature Space Christopher Small Daniel Sousa 2022-01-01T00:00:00Z https://doi.org/10.3389/frsen.2021.793228 https://doaj.org/article/6d521a44116b43e19b51576c4cbd06d5 EN eng Frontiers Media S.A. https://www.frontiersin.org/articles/10.3389/frsen.2021.793228/full https://doaj.org/toc/2673-6187 2673-6187 doi:10.3389/frsen.2021.793228 https://doaj.org/article/6d521a44116b43e19b51576c4cbd06d5 Frontiers in Remote Sensing, Vol 2 (2022) AVIRIS cryosphere hyperspectral manifold learning EOF Geophysics. Cosmic physics QC801-809 Meteorology. Climatology QC851-999 article 2022 ftdoajarticles https://doi.org/10.3389/frsen.2021.793228 2022-12-31T16:29:35Z Multispectral and hyperspectral feature spaces are useful for a variety of remote sensing applications ranging from spectral mixture modeling to discrete thematic classification. In many of these applications, models are used to project the higher dimensional continuum of reflectances (or radiances) onto lower dimensional mappings of the image target’s physical properties or categorical composition. In such cases, characterization of the feature space dimensionality, geometry and topology can provide fundamental guidance for effective model design. Utility of this characterization, however, hinges on identification of appropriate basis vectors for the feature space. The objective of this study is to compare and contrast two fundamentally different approaches for identifying feature space basis vectors via dimensionality reduction. In so doing, we illustrate how these two approaches can be combined to render a joint characterization that reveals spectral properties not apparent using either approach alone. We use a diverse collection of AVIRIS-NG reflectance spectra of ice and snow to illustrate the utility of the joint characterization to facilitate both modeling and classification of snow and ice reflectance. Joint characterization is also shown to assist with interpretation of physical properties inferred from the spectra. Spectral feature spaces combining principal components (PCs) and t-distributed Stochastic Neighbor Embeddings (t-SNEs) provide both physically interpretable dimensions representing the global structure of cryospheric reflectance properties as well as local manifold structures revealing clustering not resolved within the global continuum. The joint characterization reveals distinct continua for snow-firn gradients on different parts of the Greenland Ice Sheet and multiple clusters of ice reflectance properties common to both glacier and sea ice in different locations. The clustering revealed in the t-SNE feature spaces, and extended to the joint characterization, distinguishes subtle ... Article in Journal/Newspaper glacier Greenland Ice Sheet Sea ice Directory of Open Access Journals: DOAJ Articles Greenland Frontiers in Remote Sensing 2 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
AVIRIS cryosphere hyperspectral manifold learning EOF Geophysics. Cosmic physics QC801-809 Meteorology. Climatology QC851-999 |
spellingShingle |
AVIRIS cryosphere hyperspectral manifold learning EOF Geophysics. Cosmic physics QC801-809 Meteorology. Climatology QC851-999 Christopher Small Daniel Sousa Joint Characterization of the Cryospheric Spectral Feature Space |
topic_facet |
AVIRIS cryosphere hyperspectral manifold learning EOF Geophysics. Cosmic physics QC801-809 Meteorology. Climatology QC851-999 |
description |
Multispectral and hyperspectral feature spaces are useful for a variety of remote sensing applications ranging from spectral mixture modeling to discrete thematic classification. In many of these applications, models are used to project the higher dimensional continuum of reflectances (or radiances) onto lower dimensional mappings of the image target’s physical properties or categorical composition. In such cases, characterization of the feature space dimensionality, geometry and topology can provide fundamental guidance for effective model design. Utility of this characterization, however, hinges on identification of appropriate basis vectors for the feature space. The objective of this study is to compare and contrast two fundamentally different approaches for identifying feature space basis vectors via dimensionality reduction. In so doing, we illustrate how these two approaches can be combined to render a joint characterization that reveals spectral properties not apparent using either approach alone. We use a diverse collection of AVIRIS-NG reflectance spectra of ice and snow to illustrate the utility of the joint characterization to facilitate both modeling and classification of snow and ice reflectance. Joint characterization is also shown to assist with interpretation of physical properties inferred from the spectra. Spectral feature spaces combining principal components (PCs) and t-distributed Stochastic Neighbor Embeddings (t-SNEs) provide both physically interpretable dimensions representing the global structure of cryospheric reflectance properties as well as local manifold structures revealing clustering not resolved within the global continuum. The joint characterization reveals distinct continua for snow-firn gradients on different parts of the Greenland Ice Sheet and multiple clusters of ice reflectance properties common to both glacier and sea ice in different locations. The clustering revealed in the t-SNE feature spaces, and extended to the joint characterization, distinguishes subtle ... |
format |
Article in Journal/Newspaper |
author |
Christopher Small Daniel Sousa |
author_facet |
Christopher Small Daniel Sousa |
author_sort |
Christopher Small |
title |
Joint Characterization of the Cryospheric Spectral Feature Space |
title_short |
Joint Characterization of the Cryospheric Spectral Feature Space |
title_full |
Joint Characterization of the Cryospheric Spectral Feature Space |
title_fullStr |
Joint Characterization of the Cryospheric Spectral Feature Space |
title_full_unstemmed |
Joint Characterization of the Cryospheric Spectral Feature Space |
title_sort |
joint characterization of the cryospheric spectral feature space |
publisher |
Frontiers Media S.A. |
publishDate |
2022 |
url |
https://doi.org/10.3389/frsen.2021.793228 https://doaj.org/article/6d521a44116b43e19b51576c4cbd06d5 |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
glacier Greenland Ice Sheet Sea ice |
genre_facet |
glacier Greenland Ice Sheet Sea ice |
op_source |
Frontiers in Remote Sensing, Vol 2 (2022) |
op_relation |
https://www.frontiersin.org/articles/10.3389/frsen.2021.793228/full https://doaj.org/toc/2673-6187 2673-6187 doi:10.3389/frsen.2021.793228 https://doaj.org/article/6d521a44116b43e19b51576c4cbd06d5 |
op_doi |
https://doi.org/10.3389/frsen.2021.793228 |
container_title |
Frontiers in Remote Sensing |
container_volume |
2 |
_version_ |
1766009543676919808 |