RAPID CLASSIFICATION OF INFRA-RED HYPERSPECTRAL IMAGERY OF ROCKS - - PowerPoint PPT Presentation

▶
rapid classification of infra red hyperspectral imagery
SMART_READER_LITE
LIVE PREVIEW

RAPID CLASSIFICATION OF INFRA-RED HYPERSPECTRAL IMAGERY OF ROCKS - - PowerPoint PPT Presentation

Oct 23, 2022 290 likes •622 views

RAPID CLASSIFICATION OF INFRA-RED HYPERSPECTRAL IMAGERY OF ROCKS WITH DECISION TREES AND WAVELENGTH IMAGES F.J.A. VAN RUITENBEEK, H.M.A VAN DER WERFF, W.H. BAKKER, F.D. VAN DER MEER, C.H. HECKER, K.A.A. HEIN INTRODUCTION Specim

slide-1
SLIDE 1

RAPID CLASSIFICATION OF INFRA-RED HYPERSPECTRAL IMAGERY OF ROCKS WITH DECISION TREES AND WAVELENGTH IMAGES

F.J.A. VAN RUITENBEEK, H.M.A VAN DER WERFF, W.H. BAKKER, F.D. VAN DER MEER, C.H. HECKER, K.A.A. HEIN

slide-2
SLIDE 2
  • Specim hyperspectral camera, sisuchema setup
  • Wavelength range: 1000-2500 nm (short-wavelength infrared)
  • # pixels across: 384
  • Spatial resolution: 26 µm

INTRODUCTION

Specim.fi

slide-3
SLIDE 3

INFRA-RED HYPERSPECTRAL IMAGE ACQUIRED WITH SISUCHEMA

Pixel size: 26 µm 384 pixels 1396 pixels Reflectance at 1650 nm:

1650nm Silicified, sericitized dacite‐andesite

slide-4
SLIDE 4
  • Provides detailed information on mineralogical composition and

microstructure of rocks

  • Enables characterization of rock type and rock forming processes
  • Spatial scale comparable to “traditional” thin section
  • Input in predictive modeling of rock chemistry, e.g. ore grade, and
  • ther physical-chemical parameters

USE OF HIGH SPATIAL RESOLUTION IR IMAGERY

slide-5
SLIDE 5
  • Image-sizes are typically large (> 1 GB per raw image)
  • Images contain many pixels ( ~ 1 million per image) and bands

(288)

  • Easy generation of large volumes of image data (1 image

acquired in ~5 minutes, incl. sample preparation)

  • Interpretation of imagery is labor intensive and time consuming

(and often subjective)

PROBLEM

Methods are needed for rapid assessment of mineralogical composition

slide-6
SLIDE 6

SISUCHEMA VERSUS HYMAP

~512 pixels 126 bands 450‐2500nm

Hymap (airborne sensor) SisuChema

384 pixels 288 bands 1000‐2500nm

Atmospheric interference

slide-7
SLIDE 7

SISUCHEMA VERSUS ASD

1 point spectrum 2151 bands 350‐2500nm

ASD SisuChema

384 pixels 288 bands 1000‐2500nm

slide-8
SLIDE 8

Many strategies involve spectral matching of image and reference spectra and thresholding, e.g. Spectral Angle Mapper Limitations of these methods:

  • A prioiry knowledge of scene is required for the selection of

reference spectra

  • Matching statistics doesn’t show which parts of the spectrum

match best (hull shape vs. absorption feature) and which do not

  • Selection of threshold for a “match” is rather subjective

INTERPRETATION OF HYPERSPECTRAL IMAGERY

slide-9
SLIDE 9

MATCHING OF IMAGE AND REFERENCE SPECTRA

Is this a good match?

Molecular bond

slide-10
SLIDE 10
  • Wavelength position of absorption features is used as the

dominant spectral charateristic in the interpretation of reflectance spectra

  • It is directly related to molecular bond in crystal lattice and often

specific to (groups) of minerals

  • This information is extracted from wavelength images calculated

from the IR imagery

  • A decision tree is used for classification of the wavelength

imagery

APPROACH IN THIS STUDY

slide-11
SLIDE 11

CALCULATION OF WAVELENGTH POSITION

where w(x) is the interpolated reflectance value atposition x; x is the wavelength position in μm; a,b,c are the coefficients of the parabola function. where wmin is the interpolated wavelength position at minimum reflectance; a,b is the coefficients of the parabola function. where depth is the interpolated depth of absorption feature.

slide-12
SLIDE 12

W1, D1: Wavelength and depth of deepest feature W2, D2: Wavelength and depth of 2nd feature W3, D3: Wavelength and depth of 3rd feature W1 D1 W3 D3 W2 D2

Wavelength map W1 fused with D1

2100nm 2400nm

Wavelength image

slide-13
SLIDE 13
  • Only for exploratory analysis -> no classified mineral map
  • Small variation in wavelength positions often not visible
  • Deep absorption features dominate over shallow features

LIMITATION OF WAVELENGTH MAPPING

slide-14
SLIDE 14

Silicified, chloritised amygdaloidal (dacite)‐andesite

Amygdale L: 3.2mm PP Amygdale L: 3.2mm XP

classification using decision trees

Classified map D1 > 0.05 W1 > 2225nm W1 > 2300nm Scatter plot of wavelength image

2100nm 2400nm

Wavelength image

slide-15
SLIDE 15
  • Based on analysis absorption features in spectra of USGS

spectral library and other spectra (total of 400+ spectra)

DESIGN OF DECISION TREE

Decision tree 2100‐2400nm (Al‐OH, Fe‐OH, Mg‐OH & carbonate features):

slide-16
SLIDE 16

W1 2200‐2210 W2 2340‐2400 W1 2210‐2220 W2 2340‐2400 W1 2200‐2210 W2 2160‐2280

CLASSIFICATION WITH DECISION TREE

chalcedony_cu91‐6a.4502.asc hydrogrossular_nmnh120555.10236.asc illite_gds4.10903.asc illite_imt1.10982.asc illite_imt1.11041.asc montmorillonite_saz1.14498.asc montmorillonite_sca2.14557.asc muscovite_gds116.15173.asc muscovite_gds118.15287.asc muscovite_hs24.15512.asc muscovite_il107.15566.asc vesuvianite_hs446.23527.asc dickite_nmnh46967.6913.asc endellite_gds16.7379.asc halloysite_cm13.8921.asc kaolinite_cm3.11788.asc kaolinite_cm5.11846.asc kaolinite_cm7.11904.asc kaolinite_cm9.11962.asc kaolinite_gds11.12060.asc kaolinite_kga1.12117.asc kaolinite_kl502.12272.asc kaolinite_pfn1_kga2.12176.asc goethite_mpcma2b.8351.asc illite_il105.10969.asc lepidolite_nmnh105541.12766.asc lepidolite_nmnh88526‐1.12832.asc margarite_gds106.13344.asc montmorillonite_cm20.14324.asc montmorillonite_cm26.14382.asc muscovite_gds107.14887.asc muscovite_gds114.15116.asc muscovite_gds117.15230.asc muscovite_gds119.15344.asc muscovite_gds120.15401.asc muscovite_hs146.15457.asc nanohematite_br93‐34b2.15589.asc

  • rthoclase_hs13.17283.asc

roscoelite_en124.19682.asc spodumene_hs210.21114.asc tourmaline_hs282.22996.asc

Short‐list of candidate spectra

Albedo – R1650 Rock sample: Silicified, sericitised amydaloidal andesite Classified

slide-17
SLIDE 17

W1 2200‐2210 W2 2340‐2400 W1 2210‐2220 W2 2340‐2400 W1 2200‐2210 W2 2160‐2280

CLASSIFICATION WITH DECISION TREE

dickite_nmnh46967.6913.asc endellite_gds16.7379.asc halloysite_cm13.8921.asc kaolinite_cm3.11788.asc kaolinite_cm5.11846.asc kaolinite_cm7.11904.asc kaolinite_cm9.11962.asc kaolinite_gds11.12060.asc kaolinite_kga1.12117.asc kaolinite_kl502.12272.asc kaolinite_pfn1_kga2.12176.asc

Short‐list of candidate spectra

Rock sample: Silicified, sericitised amydaloidal andesite Albedo – R1650 Classified

slide-18
SLIDE 18

W1 2200‐2210 W2 2340‐2400 W1 2210‐2220 W2 2340‐2400 W1 2200‐2210 W2 2160‐2280

CLASSIFICATION WITH DECISION TREE

dickite_nmnh46967.6913.asc endellite_gds16.7379.asc halloysite_cm13.8921.asc kaolinite_cm3.11788.asc kaolinite_cm5.11846.asc kaolinite_cm7.11904.asc kaolinite_cm9.11962.asc kaolinite_gds11.12060.asc kaolinite_kga1.12117.asc kaolinite_kl502.12272.asc kaolinite_pfn1_kga2.12176.asc

Short‐list of candidate spectra

Rock sample: Silicified, sericitised amydaloidal andesite

Amygdale 2.5mm

Albedo – R1650 Classified

slide-19
SLIDE 19
  • Hydrothermally altered rocks
  • Associated with VMS Cu-Zn deposits
  • Pervasive alteration of volcanic rock
  • Archean (3.2 Ga) submarine setting

CASE STUDY

slide-20
SLIDE 20

Albedo – reflectance at 1650nm Weakly sericite altered and silicified muddy chert Silicified, seriticized xenocrystic‐ phenocrystic (dacite)‐andesite Silicified, sericitized phenocrystic (dacite)‐andesite Silicified, sericitized weakly phenocrystic dacite Silicified, sericitized weakly phenocrystic quenched dacite Silicified, sericitized weakly phenocrystic dacite Silicified, sericitized amygdaloidal andesite Silicified, sericitized weakly amydaloidal titanium‐rich andesite Ferruginous, chloritised basalt Ferruginous, chloritized (pyroxene‐ bearing) andesite Silicified, and chloritised amygdaloidal (dacite)‐andesite Micrograph thin section

slide-21
SLIDE 21

Al‐rich illite‐ muscovite <2210nm Shallow Fe‐OH feature 2260‐ 2300nm Fe‐chlorite Al‐poor illite‐ muscovite >2210nm kaolinite Al‐rich illite‐ muscovite < 2203nm – chert Chlorite Mg‐Fe chlorite

Interpreted mineralogy:

Albedo – reflectance at 1650nm Classification – general decision tree

Pervasive alteration Pervasive alteration Illite‐muscovite alteration Kaolinite filled amygdales Illite‐musc rich amygdales Zonation:

  • Al‐rich illite‐muscovite
  • Al‐poor illite‐muscovite
  • Chorite +/‐ illite‐muscovite
slide-22
SLIDE 22
  • Classification of wavelength images with decision trees provides

method for rapid assessment of mineral composition

  • No a priory information on mineralogy of rock sample is required
  • Focus on mineral absorption features (diagnostic for many

minerals, unlike hull-shapes)

  • Objective and reproducible result

SUMMARY AND CONCLUSIONS

slide-23
SLIDE 23
  • Scene-specific optimization of decision tree
  • Automation of processing steps
  • Extraction of microstructural / textural information

FURTHER WORK

slide-24
SLIDE 24

Spare slides:

slide-25
SLIDE 25

Objective: To optimize decision tree for specific scene – sample set

  • Enhancement of spectral variation in wavelength images
  • Calculation of summary products, such as illite and kaolinite

crystallinity, ferrous drop, etc

  • Visual-spatial analysis of contrast enhanced images and selection
  • f additional end member ROIs
  • Analysis of ROIs: Spectra and scatter plots of wavelength

positions and depth of absorption features and summary products

  • Improvement of slicing intervals and update of decision tree

STEP 2 – DETAILED IMAGE ANALYSIS

slide-26
SLIDE 26

Albedo: Reflectance at 1650nm Illite‐musc crystallinity

Summary product: Illite‐musc crystallinity = Depth H20 / Depth Al‐OH

Depth Al‐OH Depth H20 Classified with decision tree CC of W1, W2,W3 between 1850‐ 2100nm

slide-27
SLIDE 27

ROIs

Illite‐musc crystallinity Albedo: Reflectance at 1650nm

slide-28
SLIDE 28

Illite‐musc crystallinity 3.25 2 phenocrysts matrix xenocrysts Albedo: Reflectance at 1650nm

slide-29
SLIDE 29

Illite‐musc crystallinity Classified with decision tree

Update decision three with crystallinity data

Illite/muscovite matrix Well‐ordered illite/muscovite phenocryst Poorly‐ordered illite/muscovite

Interpretation: Phenocryst Length: 1.4 mm Xenocryst Length: 2 mm

slide-30
SLIDE 30

Albedo – reflectance at 1650nm Weakly sericite altered and silicified muddy chert Silicified, seriticized xenocrystic‐ phenocrystic (dacite)‐andesite Silicified, sericitized phenocrystic (dacite)‐andesite Silicified, sericitized weakly phenocrystic dacite Silicified, sericitized weakly phenocrystic quenched dacite Silicified, sericitized weakly phenocrystic dacite Silicified, sericitized amygdaloidal andesite Silicified, sericitized weakly amydaloidal titanium‐rich andesite Ferruginous, chloritised basalt Ferruginous, chloritized (pyroxene‐ bearing) andesite Silicified, and chloritised amygdaloidal (dacite)‐andesite Micrograph thin section

slide-31
SLIDE 31

Al‐rich illite‐ muscovite <2210nm Shallow Fe‐OH feature 2260‐ 2300nm Fe‐chlorite Al‐poor illite‐ muscovite >2210nm kaolinite Al‐rich illite‐ muscovite < 2203nm – chert Chlorite Mg‐Fe chlorite Ordered illite/muscovite Disordered illite/muscovite “Ordered” kaolinite Ordered illite/muscovite Disordered illite/muscovite

Interpreted mineralogy:

Albedo – reflectance at 1650nm Classification – general decision tree

Pervasive alteration Pervasive alteration Illite‐muscovite alteration Kaolinite filled amygdales Illite‐musc rich amygdales Zonation:

  • Al‐rich illite‐muscovite
  • Al‐poor illite‐muscovite
  • Chorite +/‐ illite‐muscovite
slide-32
SLIDE 32

Albedo – reflectance at 1650nm Classification – general decision tree Classification –decision tree ‐ sample specific

Al‐rich illite‐ muscovite <2210nm Shallow Fe‐OH feature 2260‐ 2300nm Fe‐chlorite Al‐poor illite‐ muscovite >2210nm kaolinite Al‐rich illite‐ muscovite < 2203nm – chert Chlorite Mg‐Fe chlorite Ordered illite/muscovite Disordered illite/muscovite “Ordered” kaolinite Ordered illite/muscovite Disordered illite/muscovite

Interpreted mineralogy:

Phenocrysts Xenocrysts Amygdales Volcanic texture!