A sparse Gaussian sigmoid basis function approximation of hyperspectral data for detection of solids

Lanker, Cory L.; Smith, Milton O.

doi:10.1002/sam.11433

Title: A sparse Gaussian sigmoid basis function approximation of hyperspectral data for detection of solids

Abstract

Abstract We define a new characterization of emissivity and reflectance curves for compositional exploitation of hyperspectral data. Our method decomposes each spectrum into a sparse set of Gaussian sigmoid components using penalized regression. Detection is based on the combination of Gaussian sigmoid components unique to a target material. Focusing on the presence of spectral upslopes and downslopes rather than spectral correlations makes detection more robust to both target variation and spectral variability from atmosphere and background encountered during the collection process. We present simulation studies that demonstrate the potential to reduce false positive rates without compromising sensitivity. Characterization of long‐wave infrared (LWIR) experimental data validates our method using minerals of different particle sizes, measurement angles, and collection conditions.

Authors:

^[1]; Smith, Milton O. ^[1]

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Publication Date:: 2019-07-30

Research Org.:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Org.:: USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation

OSTI Identifier:: 1575862

Alternate Identifier(s):: OSTI ID: 1545646

Report Number(s):: LLNL-JRNL-753011
Journal ID: ISSN 1932-1864; 939031

Grant/Contract Number:: AC52-07NA27344

Resource Type:: Accepted Manuscript

Journal Name:: Statistical Analysis and Data Mining

Additional Journal Information:: Journal Volume: 12; Journal Issue: 6; Journal ID: ISSN 1932-1864

Publisher:: Wiley

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; basis function decomposition; classification; curve fitting; feature extraction; LASSO regression; minerals; spectral characterization; target detection

Citation Formats


                    Lanker, Cory L., and Smith, Milton O. A sparse Gaussian sigmoid basis function approximation of hyperspectral data for detection of solids.  United States: N. p., 2019. 
Web.  doi:10.1002/sam.11433.

Copy to clipboard


                    Lanker, Cory L., & Smith, Milton O. A sparse Gaussian sigmoid basis function approximation of hyperspectral data for detection of solids.  United States.  https://doi.org/10.1002/sam.11433

Copy to clipboard


                    Lanker, Cory L., and Smith, Milton O. Tue .  
"A sparse Gaussian sigmoid basis function approximation of hyperspectral data for detection of solids".  United States.  https://doi.org/10.1002/sam.11433.  https://www.osti.gov/servlets/purl/1575862.

Copy to clipboard


                    
@article{osti_1575862,

  title        = {A sparse Gaussian sigmoid basis function approximation of hyperspectral data for detection of solids},

  author       = {Lanker, Cory L. and Smith, Milton O.},

  abstractNote = {Abstract We define a new characterization of emissivity and reflectance curves for compositional exploitation of hyperspectral data. Our method decomposes each spectrum into a sparse set of Gaussian sigmoid components using penalized regression. Detection is based on the combination of Gaussian sigmoid components unique to a target material. Focusing on the presence of spectral upslopes and downslopes rather than spectral correlations makes detection more robust to both target variation and spectral variability from atmosphere and background encountered during the collection process. We present simulation studies that demonstrate the potential to reduce false positive rates without compromising sensitivity. Characterization of long‐wave infrared (LWIR) experimental data validates our method using minerals of different particle sizes, measurement angles, and collection conditions.},

  doi          = {10.1002/sam.11433},

  journal      = {Statistical Analysis and Data Mining},

  number       = 6,

  volume       = 12,

  place        = {United States},

  year         = {2019},

  month        = {7}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (Publisher)

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1002/sam.11433

Other availability

Search WorldCat to find libraries that may hold this journal

Figures / Tables:

FIGURE 1: Calcite LWIR emissivity spectra for various sieved particle sizes as published in [6]. The common calcite chemistry causes spectral upslopes and downslopes with similar locations and widths but with varying relative amplitudes due to particle morphology.

All figures and tables (9 total)

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Gaussian analysis of temperature effects on the reflectance spectra of mafic minerals in the 1-μm region
journal, January 1986

Roush, Ted L.; Singer, Robert B.
Journal of Geophysical Research, Vol. 91, Issue B10
DOI: 10.1029/JB091iB10p10301

Water frost and ice: The near-infrared spectral reflectance 0.65-2.5 μm
journal, April 1981

Clark, Roger N.
Journal of Geophysical Research: Solid Earth, Vol. 86, Issue B4
DOI: 10.1029/JB086iB04p03087

Midinfrared optical constants of calcite and their relationship to particle size effects in thermal emission spectra of granular calcite
journal, June 1999

Lane, Melissa D.
Journal of Geophysical Research: Planets, Vol. 104, Issue E6
DOI: 10.1029/1999JE900025

Least angle regression
journal, April 2004

Tibshirani, Robert; Johnstone, Iain; Hastie, Trevor
The Annals of Statistics, Vol. 32, Issue 2
DOI: 10.1214/009053604000000067

Enhanced detection of solids from Gaussian spectral features
conference, July 2017

Lanker, Cory; Smith, Milton O.
2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
DOI: 10.1109/IGARSS.2017.8127209

Regression Shrinkage and Selection Via the Lasso
journal, January 1996

Tibshirani, Robert
Journal of the Royal Statistical Society: Series B (Methodological), Vol. 58, Issue 1
DOI: 10.1111/j.2517-6161.1996.tb02080.x

Estimating modal abundances from the spectra of natural and laboratory pyroxene mixtures using the modified Gaussian model
journal, May 1993

Sunshine, Jessica M.; Pieters, Carlé M.
Journal of Geophysical Research: Planets, Vol. 98, Issue E5
DOI: 10.1029/93JE00677

Optimization of probiotic therapeutics using machine learning in an artificial human gastrointestinal tract
journal, January 2021

Westfall, Susan; Carracci, Francesca; Estill, Molly
Scientific Reports, Vol. 11, Issue 1
DOI: 10.1038/s41598-020-79947-y

Hyperspectral remote sensing
text, January 2013

Ben Dor, Eyal; Malthus, Tim; Plaza, Antonio J.
Wiley-VCH
DOI: 10.5167/uzh-86616

Hyperspectral remote sensing
text, January 2005

Rai, Suchit
Unpublished
DOI: 10.13140/rg.2.2.30289.22884

The Elements of Statistical Learning
book, January 2001

Hastie, Trevor; Friedman, Jerome; Tibshirani, Robert
Springer Series in Statistics
DOI: 10.1007/978-0-387-21606-5

Figures / Tables found in this record:

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

Similar Records in DOE PAGES and OSTI.GOV collections:

Hyperspectral Data Approximation by Gaussian Sigmoids

Software Lanker, Cory L ; USDOE National Nuclear Security Administration

Finds LASSO fit coefficient values of hyperspectral data for a Gaussian sigmoid basis function collection using LARS (least angle regression) methodology on a provided vector of sensor wavelength bins.
https://doi.org/10.11578/dc.20190826.1

View Software
Dose-shaping using targeted sparse optimization

Journal Article Sayre, George A. ; Ruan, Dan - Medical Physics

Purpose: Dose volume histograms (DVHs) are common tools in radiation therapy treatment planning to characterize plan quality. As statistical metrics, DVHs provide a compact summary of the underlying plan at the cost of losing spatial information: the same or similar dose-volume histograms can arise from substantially different spatial dose maps. This is exactly the reason why physicians and physicists scrutinize dose maps even after they satisfy all DVH endpoints numerically. However, up to this point, little has been done to control spatial phenomena, such as the spatial distribution of hot spots, which has significant clinical implications. To this end, themore »« less
https://doi.org/10.1118/1.4808363
Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding

Patent Moody, Daniela ; Wohlberg, Brendt

An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial texturalmore »« less
Full Text Available
Development of Research Infrastructure in Nevada for the Exploitation of Hyperspectral Image Data to Address Proliferation and Detection of Chemical and Biological Materials.

Technical Report Taranik, James V

This research was to exploit hyperspectral reflectance imaging technology for the detection and mapping variability (clutter) of the natural background against which gases in the atmosphere are imaged. The natural background consists of landscape surface cover composed of consolidated rocks, unconsolidated rock weathering products, soils, coatings on rock materials, vegetation, water, materials constructed by humans, and mixtures of the above. Human made gases in the atmosphere may indicate industrial processes important to detecting non-nuclear chemical and biological proliferation. Our research was to exploit the Visible and Near-Infrared (NIR) and the Short-wave Infrared (SWIR) portions of the electromagnetic spectrum to determinemore »« less
https://doi.org/10.2172/927090

Full Text Available
Improving Spectral Image Classification through a Custom Data Sparsing and Pixel Clustering Algorithm

Conference McKenna, Ian ; Kimblin, Clare ; Burt, Christopher ; ...

The Underground Nuclear Explosion Signatures Experiment (UNESE) seeks to characterize non-prompt observables from underground nuclear explosions (UNE). As part of this effort, we evaluated the ability of Digital Globe’s World View-3 (WV3) to detect and map UNE signatures. WV3 has proven capabilities in the detection of large-scale, anomalous, man-made features; however, it has relatively limited spectral and spatial resolution as compared to airborne hyperspectral imaging. These limitations impede standard image classifiers from identifying UNE signatures that are spatially small and lack distinct spectral features. In order to improve image classification results, we developed a custom algorithm that increases the truemore »« less
Full Text Available

Similar Records

Title: A sparse Gaussian sigmoid basis function approximation of hyperspectral data for detection of solids

Abstract

Citation Formats

Figures / Tables:

Gaussian analysis of temperature effects on the reflectance spectra of mafic minerals in the 1-μm region journal, January 1986

Water frost and ice: The near-infrared spectral reflectance 0.65-2.5 μm journal, April 1981

Midinfrared optical constants of calcite and their relationship to particle size effects in thermal emission spectra of granular calcite journal, June 1999

Least angle regression journal, April 2004

Enhanced detection of solids from Gaussian spectral features conference, July 2017

Regression Shrinkage and Selection Via the Lasso journal, January 1996

Estimating modal abundances from the spectra of natural and laboratory pyroxene mixtures using the modified Gaussian model journal, May 1993

Optimization of probiotic therapeutics using machine learning in an artificial human gastrointestinal tract journal, January 2021

Hyperspectral remote sensing text, January 2013

Hyperspectral remote sensing text, January 2005

The Elements of Statistical Learning book, January 2001

Gaussian analysis of temperature effects on the reflectance spectra of mafic minerals in the 1-μm region
journal, January 1986

Water frost and ice: The near-infrared spectral reflectance 0.65-2.5 μm
journal, April 1981

Midinfrared optical constants of calcite and their relationship to particle size effects in thermal emission spectra of granular calcite
journal, June 1999

Least angle regression
journal, April 2004

Enhanced detection of solids from Gaussian spectral features
conference, July 2017

Regression Shrinkage and Selection Via the Lasso
journal, January 1996

Estimating modal abundances from the spectra of natural and laboratory pyroxene mixtures using the modified Gaussian model
journal, May 1993

Optimization of probiotic therapeutics using machine learning in an artificial human gastrointestinal tract
journal, January 2021

Hyperspectral remote sensing
text, January 2013

Hyperspectral remote sensing
text, January 2005

The Elements of Statistical Learning
book, January 2001