Mapping nonnative plants using hyper spectral imagery

1
Mapping nonnative plants using
hyper spectral imagery

• Emma Underwood
• Susan Ustin
• Deanne Dipietro

2
Outline

• Introduction
• Methodology
• Results
• Discussion
• Conclusions

3
Introduction

• Nonnative plants are plants that have been
  introduced in to the environment intentionally or
  accidentally by human activity.
• Threaten - global diversity
• - ecosystem functioning
• Pimentel et al (2000) estimated that 50,000
  invasive species have been introduced into the
  U.S. causing economic losses of 137 billion per
  year approximately 35 billion annual cost for
  plant invasions alone.

4

• The global extent and rapid increase in invasive
  species is recognized as a primary cause of
  global biodiversity loss.
• Nowhere is the ecological threat more clearly
  seen than in California where more than 1025
  plant species have been added to the flora
  (Rejmánek Randall, 1994).

5
Ice plant(Carpobrotus edulis)

• Common ice plant (Carpobrotus edulis), is an
  exotic plant species that invades coastal plant
  communities from the North Coast of California to
  Mexico.
• CalEPPC (1999) rated C. edulis as an A-1 species
  (The Most Invasive Wild land Pest Plant
  Widespread).

6
Jubata grass (Cortaderia jubata)

• Poses a significant threat to mediterranen
  ecosystems
• prolific wind dispersed seeds
• tolerance of a broad range of habitats and
• its competitiveness for light,moisture,and
  nutrients(Cowen,1976).

7

• Key requirement
• Delineation the spatial extent
• Severity or intensity of invasion
• Provides
• baseline for monitoring future expansion
• assists in identifying targets for control
  activities

8

Remote sensing-invasive plants mapping

• Offers significant opportunities for providing
  timely information on invasions of nonnative
  species into native habitats.
• Larger spatial area
• Short period of time
• Researchers exploit unique phenological,
  spectral, or structural characteristics of the
  nonnative species in the image to distinguish
  them from the mosaic of species around them.

9

• Two ways
• High spatial ,but low spectral resolution-black
  white or color infrared aerial photographs
• Digital images with greater spectral resolution
  although coarser spatial resolution.
• Aerial photography - inexpensive,
• - large amount
  of archival data
• - very fine
  spatial resolution
• But
• - relies on nonnative
  plant possessing visually
  detectable unique characteristics
• - Extensive manual labor
• - Can collect data over a
  relatively small spatial area

10

• Digital multispectral imagery- automated image
  processing
• 
  - large spatial coverage
• Successful applications of AVHRR, TM and ADAR
• However, invasive species
  populations Can be detected only after they
  become dense and widespread.

11
AVIRIS (Airborne Visible/infrared imaging
spectrometer)

• Increased spatial resolution
• Fine spectral resolution
• 224 spectral bands
• 400-2500nm at 10nm resolution
• 20 m spatial resolution when flying at 11km.

12

• Limitations of using traditionally available
  wavebands
• - with color infrared green vegetation is
  observed as shades of red.

13
Objective

• To investigate the use of AVIRIS imagery to
  detect the invasive species ice plant
  (Carpobrotus edulis) and Jubata grass(Cortaderia
  jubata).
• To compare three techniques for processing the
  imagery minimum noise fraction(MNF),Continuum
  removal ,and band ratio indices.

14
Study site

• VAFB is used primarily for developing and testing
  missiles and satellite launches for the
  Department of Defense and NASA.
• 836 Vascular plants-quarter of them are invasive
  species.
• C.edulis and C.jubata have invaded two native
  community types coastal dune scrub community and
  maritime chaparral.

15

• The focus of this research is the encroachment
  of ice plant and jubata grass in to these native
  communities and specifically on the ability of
  AVIRIS to identify pixels of different densities
  of these species.

16
Field work at VAFB
17
Methodology

• Pre-processing
• - Atmospheric correction
• - Masks( NDVI gt 0.2)
• Processing
• - Minimum Noise Fraction
• - Continuum Removal
• - Band Ratios
• Compared processing
  techniques
• - Ability to delineate iceplant extent
• - Detect iceplant density
• - Assess ease of processing and repeatability

18
Image Classification

• Supervised Classification requires the user to
  decide which classes exist in the
  image, and then These samples known as training
  areas and are then input into a classification
  program, which produces a classified image.

• Type of supervised ClassificationMaximum
  likelihood classifier
• Maximum likelihood classification calculates the
  probability that a given pixel belongs to a
  specific class.

19

• Unsupervised Classification when features are
  separated solely on their spectral properties .
• Processing Techniques
• Minimum Noise fraction(MNF) Often used method
  for reducing redundancy of information between
  bands
• reduce and compress the data
• increase speed of processing

20
Continuum removal is a procedure that
facilitates the distinction of similar absorption
bands in hyper spectral curves.
21
Band ratio indices

• Emphasize the biochemical and the biophysical
  properties of the vegetation contained in
  physiologically important bands.

22
Definitions

• Confusion matrix is a square array of numbers
  set out in rows and columns which express the
  number of sample units(i.e.,pixels,clusters of
  pixels etc..) assigned to a particular category
  relative to the actual category as verified on
  the ground.
• Overall accuracy-the total number of correctly
  classified samples( i.e,the major diagonal)
  divided by the total number of sample units in
  the entire matrix.

23

• Producers accuracy is the number of correctly
  classified samples of a particular category
  divided by the total number of reference samples
  from that category.
• Users accuracy is the number of correctly
  classified samples of a particular category
  divided by the total number of samples being
  classified as that category.

24
ResultsComparison of 3 processing techniques
25
Results

• Overall accuracy-MNF performed best
• Users accuracy-is important
• Users accuracy-MNF lowest
• MNF is able to produce a more accurate map of
  multiple vegetation classes
• Continuum removal and band ratio techniques are
  suited for detecting species with distinct
  characteristics.

26
Discussion

• Evaluated three approaches- accuracy
• -
  logistics of processing
• -
  ease of interpretation
• Confusion matrices demonstrated that MNF
  performed best for classifying all five
  vegetation communities.
• However,in terms of classifying one of the target
  species,ice plant,the continuum removal and the
  band ratio methods performed better.

27
Key findings..

• MNF
• Worked well identifying different densities of
  ice plant
• X Difficult to interpret
• Band Ratio
• Intuitive
• Continuum Removal
• Good results for presence / absence of ice plant
• Easy to use
• X Speckled result, accuracy not improved when
  lumped

28
Conclusions

• The benefit of this research has been to
  contribute to the knowledge base of land managers
  at VAFB
• by providing improved information on the spatial
  extent and the density of the ice plant and
  jubata grass, which will lead to better
  protection of the native biodiversity.