An Unmixing Algorithm Based on a Large Library of Shortwave Infrared Spectra

The unmixing algorithm described in this paper has been motivated by a “spectral library” of pure shortwave infrared reflectance spectra that we started building in the early 1990’s. The library currently consists of 493 samples, representing 60 nominally pure materials (mostly minerals, but also water, dry vegetation and several man-made materials). The algorithm, implemented in software called The Spectral AssistantTM (TSA), is designed to analyse quickly tens to hundreds of thousands of spectra measured from drill core or chips using CSIRO’s HyLoggerTM and HyChips TM instruments, and other commercial reflectance spectrometers. Individual samples typically are composed of a small number of minerals. Therefore, in order to avoid overfitting, the TSA algorithm ultilises fast subset selection procedures to identify the most likely minerals in the mixture. Other novel aspects of the algorithm include the simultaneous fitting of the low frequency background with mineral identification (which provides greater model flexibility) and the combined fitting being carried out in penalised canonical variate space (which has certain optimality properties under an idealised model). The performance of the algorithm is illustrated on a few key examples. Discussion includes its wider applicability, its limitations and possible future extensions and modifications.

[1]  Alan J. Miller.  Subset Selection in Regression , 1992 .

[2]  Clifford M. Hurvich,et al.  Regression and time series model selection in small samples , 1989 .

[3]  F. J. Holler,et al.  Principles of Instrumental Analysis , 1973 .

[4]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[5]  D. Roberts,et al.  Endmember selection for multiple endmember spectral mixture analysis using endmember average RMSE , 2003 .

[6]  Hairong Qi,et al.  Endmember Extraction From Highly Mixed Data Using Minimum Volume Constrained Nonnegative Matrix Factorization , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Andreas T. Ernst,et al.  ICE: a statistical approach to identifying endmembers in hyperspectral images , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Theofanis Sapatinas,et al.  Discriminant Analysis and Statistical Pattern Recognition , 2005 .

[9]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[10]  Kamal A. Ali,et al.  Towards knowledge-based identification of mineral mixtures from reflectance spectra , 1989, Knowl. Based Syst..

[11]  Raymond Lister.  Toward context dependent classification of infra-red spectra by energy minimization , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[12]  M. D. Craig,et al.  Analysis of aircraft spectrometer data with logarithmic residuals , 1985 .

[13]  Grace Wahba,et al.  Spline Models for Observational Data , 1990 .

[14]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[15]  Maurice D. Craig,et al.  Minimum-volume transforms for remotely sensed data , 1994, IEEE Trans. Geosci. Remote. Sens..

[16]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[17]  I. Daubechies.  Ten Lectures on Wavelets , 1992 .

[18]  A. B. Lefkoff,et al.  Expert system-based mineral mapping in northern death valley, California/Nevada, using the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) , 1993 .

[19]  B. Hapke.  Theory of reflectance and emittance spectroscopy , 1993 .

[20]  R. Tibshirani,et al.  Penalized Discriminant Analysis , 1995 .

[21]  S. J. Sutley,et al.  Imaging spectroscopy: Earth and planetary remote sensing with the USGS Tetracorder and expert systems , 2003 .

[22]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.