A Supervised Method for Nonlinear Hyperspectral Unmixing
Due to the complex interaction of light with the Earth’s surface, reflectance spectra can be described as highly nonlinear mixtures of the reflectances of the material constituents occurring in a given resolution cell of hyperspectral data. Our aim is to estimate the fractional abundance m...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/20/2458 |
| _version_ | 1823960216202379264 |
|---|---|
| author | Bikram Koirala Mahdi Khodadadzadeh Cecilia Contreras Zohreh Zahiri Richard Gloaguen Paul Scheunders |
| author_facet | Bikram Koirala Mahdi Khodadadzadeh Cecilia Contreras Zohreh Zahiri Richard Gloaguen Paul Scheunders |
| author_sort | Bikram Koirala |
| collection | DOAJ |
| description | Due to the complex interaction of light with the Earth’s surface, reflectance spectra can be described as highly nonlinear mixtures of the reflectances of the material constituents occurring in a given resolution cell of hyperspectral data. Our aim is to estimate the fractional abundance maps of the materials from the nonlinear hyperspectral data. The main disadvantage of using nonlinear mixing models is that the model parameters are not properly interpretable in terms of fractional abundances. Moreover, not all spectra of a hyperspectral dataset necessarily follow the same particular mixing model. In this work, we present a supervised method for nonlinear spectral unmixing. The method learns a mapping from a true hyperspectral dataset to corresponding linear spectra, composed of the same fractional abundances. A simple linear unmixing then reveals the fractional abundances. To learn this mapping, ground truth information is required, in the form of actual spectra and corresponding fractional abundances, along with spectra of the pure materials, obtained from a spectral library or available in the dataset. Three methods are presented for learning nonlinear mapping, based on Gaussian processes, kernel ridge regression, and feedforward neural networks. Experimental results conducted on an artificial dataset, a data set obtained by ray tracing, and a drill core hyperspectral dataset shows that this novel methodology is very promising. |
| first_indexed | 2024-12-17T16:45:03Z |
| format | Article |
| id | doaj.art-59f949caa7814f4bbefed88cec88da7a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-17T16:45:03Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-59f949caa7814f4bbefed88cec88da7a2022-12-21T21:40:46ZengMDPI AGRemote Sensing2072-42922019-10-011120245810.3390/rs11202458rs11202458A Supervised Method for Nonlinear Hyperspectral UnmixingBikram Koirala0Mahdi Khodadadzadeh1Cecilia Contreras2Zohreh Zahiri3Richard Gloaguen4Paul Scheunders5IMEC-Vision Lab, Department of Physics, University of Antwerp, 2000 Antwerp, BelgiumHelmholtz Institute Freiberg for Resource Technology, 09599 Freiberg, GermanyHelmholtz Institute Freiberg for Resource Technology, 09599 Freiberg, GermanyIMEC-Vision Lab, Department of Physics, University of Antwerp, 2000 Antwerp, BelgiumHelmholtz Institute Freiberg for Resource Technology, 09599 Freiberg, GermanyIMEC-Vision Lab, Department of Physics, University of Antwerp, 2000 Antwerp, BelgiumDue to the complex interaction of light with the Earth’s surface, reflectance spectra can be described as highly nonlinear mixtures of the reflectances of the material constituents occurring in a given resolution cell of hyperspectral data. Our aim is to estimate the fractional abundance maps of the materials from the nonlinear hyperspectral data. The main disadvantage of using nonlinear mixing models is that the model parameters are not properly interpretable in terms of fractional abundances. Moreover, not all spectra of a hyperspectral dataset necessarily follow the same particular mixing model. In this work, we present a supervised method for nonlinear spectral unmixing. The method learns a mapping from a true hyperspectral dataset to corresponding linear spectra, composed of the same fractional abundances. A simple linear unmixing then reveals the fractional abundances. To learn this mapping, ground truth information is required, in the form of actual spectra and corresponding fractional abundances, along with spectra of the pure materials, obtained from a spectral library or available in the dataset. Three methods are presented for learning nonlinear mapping, based on Gaussian processes, kernel ridge regression, and feedforward neural networks. Experimental results conducted on an artificial dataset, a data set obtained by ray tracing, and a drill core hyperspectral dataset shows that this novel methodology is very promising.https://www.mdpi.com/2072-4292/11/20/2458hyperspectral unmixingspectral mixing modelsmachine learning algorithms |
| spellingShingle | Bikram Koirala Mahdi Khodadadzadeh Cecilia Contreras Zohreh Zahiri Richard Gloaguen Paul Scheunders A Supervised Method for Nonlinear Hyperspectral Unmixing Remote Sensing hyperspectral unmixing spectral mixing models machine learning algorithms |
| title | A Supervised Method for Nonlinear Hyperspectral Unmixing |
| title_full | A Supervised Method for Nonlinear Hyperspectral Unmixing |
| title_fullStr | A Supervised Method for Nonlinear Hyperspectral Unmixing |
| title_full_unstemmed | A Supervised Method for Nonlinear Hyperspectral Unmixing |
| title_short | A Supervised Method for Nonlinear Hyperspectral Unmixing |
| title_sort | supervised method for nonlinear hyperspectral unmixing |
| topic | hyperspectral unmixing spectral mixing models machine learning algorithms |
| url | https://www.mdpi.com/2072-4292/11/20/2458 |
| work_keys_str_mv | AT bikramkoirala asupervisedmethodfornonlinearhyperspectralunmixing AT mahdikhodadadzadeh asupervisedmethodfornonlinearhyperspectralunmixing AT ceciliacontreras asupervisedmethodfornonlinearhyperspectralunmixing AT zohrehzahiri asupervisedmethodfornonlinearhyperspectralunmixing AT richardgloaguen asupervisedmethodfornonlinearhyperspectralunmixing AT paulscheunders asupervisedmethodfornonlinearhyperspectralunmixing AT bikramkoirala supervisedmethodfornonlinearhyperspectralunmixing AT mahdikhodadadzadeh supervisedmethodfornonlinearhyperspectralunmixing AT ceciliacontreras supervisedmethodfornonlinearhyperspectralunmixing AT zohrehzahiri supervisedmethodfornonlinearhyperspectralunmixing AT richardgloaguen supervisedmethodfornonlinearhyperspectralunmixing AT paulscheunders supervisedmethodfornonlinearhyperspectralunmixing |