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

Thanh Bui; Beate Orberger; Simon Blancher; Ali Mohammad‐Djafari; Henry Pillière; Anne Salaün; Xavier Bourrat; Nicolas Maubec; Thomas Lefévre; Céline Rodriguez; Antanas Vaitkus; S. Gražulis; Cédric Duée; Dominique Harang; T. Wallmach; Yassine El Mendili; Daniel Chateigner; Mike Buxton; Monique Le Guen

doi:10.1109/igarss.2018.8519131

Abstract

1 min read

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.

Related publications

Article2016

Locally Similar Sparsity-Based Hyperspectral Compressive Sensing Using Unmixing

Lei Zhang, Wei Wei, Hangqi Yan, Fei Li, Chunna Tian

Article2014

Structured sparse BAYESIAN hyperspectral compressive sensing using spectral unmixing

Lei Zhang, Wei Wei, Fei Li, Hangqi Yan

Article2017

3D Imaging on heterogeneous surfaces on laterite drill core materials

Henry Pillière, T Lefevre, Dominique Harang, Beate Orberger, Thanh Q. Bui, Cédric Duée, Nicolas Maubec, Xavier Bourrat, Yassine El Mendili, Stéphanie Gascoin, Daniel Chateigner, Monique Le Guen, Anne Salaün, Céline Rodriguez, G. Mariotto, Marco Giarola, Arun Kumar, N. Daldosso, M. Zanatta, Adolfo Speghini, Andrea Sanson, Luca Lutterotti, Evgeny Borovin, Mauro Bortolotti, Maria Secchi,

Preprint2017

Combined mineralogy and chemistry on drill-cores: challenging for on-line-real-time analyses

Cédric Duée, Nicolas Maubec, Valérie Laperche, Laure Capar, Anne Bourguignon, Xavier Bourrat, Yassine El Mendili, Daniel Chateigner, Stéphanie Gascoin, G. Mariotto, Arun Kumar, M. Zanatta, Luca Lutterotti, Evgeny Borovin, Mauro Bortolotti, Maria Secchi, M. Montagna, Beate Orberger, Anne Salaün, Céline Rodriguez, Fabien Trotet, Mohamed Kadar, Karen Devaux, Henry Pillière,

Article2024

Dictionary Trained Attention Constrained Low Rank and Sparse Autoencoder for Hyperspectral Anomaly Detection

Xing Hu, Zhixuan Li, Lingkun Luo, Hamid Reza Karimi, Dawei Zhang

Neural Networks