Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification

Thanh Bui; Simon B. Blancher; Ali Mohammad-Djafari; Henry Pilliere; Antanas Vaitkus; Yassine El Mendili; Daniel Chateigner; Mike Buxton; null More Authors

doi:10.1109/IGARSS.2018.8519131

Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification

Thanh Bui, Simon B. Blancher, Ali Mohammad-Djafari, Henry Pilliere, Antanas Vaitkus, Yassine El Mendili, Daniel Chateigner, Mike Buxton, More Authors

Resource Engineering

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

The objective of the SOLSA project (EU-H2020) is to develop an analytical expert system for on-line-on-mine-real-time mineralogical and geochemical analyses on sonic drill cores. As one aspect of the system, this paper presents the building of the hyperspectral library and its incorporation into sparse unmixing techniques for mineral identification. Twenty seven spectra representing 14 minerals have been collected for the library. Three sparse unmixing techniques have been investigated and evaluated using simulated data generated from our hyperspectral library, and real hyperspectral data acquired from a serpentinized harzburgite sample. Among the three techniques, the collaborative sparse unmixing by variable splitting and augmented Lagrangian (CLSUnSAL) method provided the best accurate results on the simulated data. In addition, the results of the CLSUnSAL method show high correlation with that of the QEMSCAN® analysis on the harzburgite hyperspectral data.

Original language	English
Title of host publication	IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
Editors	Jose Moreno
Publisher	IEEE
Pages	2220-2223
Volume	2018
ISBN (Electronic)	978-1-5386-7150-4
ISBN (Print)	978-1-5386-7151-1
DOIs	https://doi.org/10.1109/IGARSS.2018.8519131
Publication status	Published - 2018
Event	IGARSS 2018: 2018 IEEE International Geoscience and Remote Sensing Symposium: Observing, Understanding And Forecasting The Dynamics Of Our Planet - Valencia, Spain Duration: 22 Jul 2018 → 27 Jul 2018 Conference number: 38 https://www.igarss2018.org/

Conference

Conference	IGARSS 2018: 2018 IEEE International Geoscience and Remote Sensing Symposium
Abbreviated title	IGARSS 2018
Country/Territory	Spain
City	Valencia
Period	22/07/18 → 27/07/18
Internet address	https://www.igarss2018.org/

Keywords

Hyperspectral library
sparse unmixing
shortwave infrared (SWIR)

Access to Document

10.1109/IGARSS.2018.8519131

Cite this

Bui, T., Blancher, S. B., Mohammad-Djafari, A., Pilliere, H., Vaitkus, A., El Mendili, Y., Chateigner, D., Buxton, M., & More Authors (2018). Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification. In J. Moreno (Ed.), IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium (Vol. 2018, pp. 2220-2223). IEEE. https://doi.org/10.1109/IGARSS.2018.8519131

@inproceedings{8445ffeeae79484ea8f1b7b9c8368847,

title = "Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification",

abstract = "The objective of the SOLSA project (EU-H2020) is to develop an analytical expert system for on-line-on-mine-real-time mineralogical and geochemical analyses on sonic drill cores. As one aspect of the system, this paper presents the building of the hyperspectral library and its incorporation into sparse unmixing techniques for mineral identification. Twenty seven spectra representing 14 minerals have been collected for the library. Three sparse unmixing techniques have been investigated and evaluated using simulated data generated from our hyperspectral library, and real hyperspectral data acquired from a serpentinized harzburgite sample. Among the three techniques, the collaborative sparse unmixing by variable splitting and augmented Lagrangian (CLSUnSAL) method provided the best accurate results on the simulated data. In addition, the results of the CLSUnSAL method show high correlation with that of the QEMSCAN{\textregistered} analysis on the harzburgite hyperspectral data.",

keywords = "Hyperspectral library, sparse unmixing, shortwave infrared (SWIR)",

author = "Thanh Bui and Blancher, {Simon B.} and Ali Mohammad-Djafari and Henry Pilliere and Antanas Vaitkus and {El Mendili}, Yassine and Daniel Chateigner and Mike Buxton and {More Authors}",

year = "2018",

doi = "10.1109/IGARSS.2018.8519131",

language = "English",

isbn = "978-1-5386-7151-1 ",

volume = "2018",

pages = "2220--2223",

editor = "Jose Moreno",

booktitle = "IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium",

publisher = "IEEE",

address = "United States",

note = "IGARSS 2018: 2018 IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding And Forecasting The Dynamics Of Our Planet, IGARSS 2018 ; Conference date: 22-07-2018 Through 27-07-2018",

url = "https://www.igarss2018.org/",

}

Bui, T, Blancher, SB, Mohammad-Djafari, A, Pilliere, H, Vaitkus, A, El Mendili, Y, Chateigner, D, Buxton, M & More Authors 2018, Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification. in J Moreno (ed.), IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium . vol. 2018, IEEE, pp. 2220-2223, IGARSS 2018: 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22/07/18. https://doi.org/10.1109/IGARSS.2018.8519131

Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification. / Bui, Thanh; Blancher, Simon B.; Mohammad-Djafari, Ali et al.
IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium . ed. / Jose Moreno. Vol. 2018 IEEE, 2018. p. 2220-2223.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification

AU - Bui, Thanh

AU - Blancher, Simon B.

AU - Mohammad-Djafari, Ali

AU - Pilliere, Henry

AU - Vaitkus, Antanas

AU - El Mendili, Yassine

AU - Chateigner, Daniel

AU - Buxton, Mike

AU - More Authors, null

N1 - Conference code: 38

PY - 2018

Y1 - 2018

N2 - The objective of the SOLSA project (EU-H2020) is to develop an analytical expert system for on-line-on-mine-real-time mineralogical and geochemical analyses on sonic drill cores. As one aspect of the system, this paper presents the building of the hyperspectral library and its incorporation into sparse unmixing techniques for mineral identification. Twenty seven spectra representing 14 minerals have been collected for the library. Three sparse unmixing techniques have been investigated and evaluated using simulated data generated from our hyperspectral library, and real hyperspectral data acquired from a serpentinized harzburgite sample. Among the three techniques, the collaborative sparse unmixing by variable splitting and augmented Lagrangian (CLSUnSAL) method provided the best accurate results on the simulated data. In addition, the results of the CLSUnSAL method show high correlation with that of the QEMSCAN® analysis on the harzburgite hyperspectral data.

AB - The objective of the SOLSA project (EU-H2020) is to develop an analytical expert system for on-line-on-mine-real-time mineralogical and geochemical analyses on sonic drill cores. As one aspect of the system, this paper presents the building of the hyperspectral library and its incorporation into sparse unmixing techniques for mineral identification. Twenty seven spectra representing 14 minerals have been collected for the library. Three sparse unmixing techniques have been investigated and evaluated using simulated data generated from our hyperspectral library, and real hyperspectral data acquired from a serpentinized harzburgite sample. Among the three techniques, the collaborative sparse unmixing by variable splitting and augmented Lagrangian (CLSUnSAL) method provided the best accurate results on the simulated data. In addition, the results of the CLSUnSAL method show high correlation with that of the QEMSCAN® analysis on the harzburgite hyperspectral data.

KW - Hyperspectral library

KW - sparse unmixing

KW - shortwave infrared (SWIR)

U2 - 10.1109/IGARSS.2018.8519131

DO - 10.1109/IGARSS.2018.8519131

M3 - Conference contribution

SN - 978-1-5386-7151-1

VL - 2018

SP - 2220

EP - 2223

BT - IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium

A2 - Moreno, Jose

PB - IEEE

T2 - IGARSS 2018: 2018 IEEE International Geoscience and Remote Sensing Symposium

Y2 - 22 July 2018 through 27 July 2018

ER -

Building a Hyperspectral Library and its Incorporation into Sparse Unmixing for Mineral Identification

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this