Spectral discrimination and classification of sugarcane
varieties using EO-1 Hyperion Hyperspectral Imagery
Armando Apan
Senior Lecturer and Coordinator, Geospatial Information and Remote Sensing Group,
Faculty of Engineering and Surveying, University of Southern Queensland,
Toowoomba 4350 QLD Australia, Phone: +61 7 4631-1386, Fax: +61 7 4631-2526,
Email: apana@usq.edu.au
Alex Held
Head, CSIRO Office of Space Science and Applications, CSIRO Earth Observation
Centre,
GPO Box 3023, Canberra ACT 2601, Australia, Phone: +61 2 6246-5718,
Fax: +61 2 6246-5988,
Email: Alex.Held@csiro.au
Stuart Phinn
Associate Professor and Leader, Biophysical Remote Sensing Group, School of
Geography,
Planning & Architecture, University of Queensland, Brisbane 4072
Australia,
Phone: +61 7 3365-6526, Fax: +61 7 3365-6899,
Email: s.phinn@uq.edu.au
John Markley
GIS Analyst, Mackay Sugar, Post Office Pleystowe, Pleystowe 4741 QLD Australia
ABSTRACT
The genetic variety of sugarcane is a major factor in many aspects of sugarcane production. It
can control growth rates, yield, sugar content, and resistance or susceptibility to pest and
diseases. Thus, reliable auditing of the varieties grown in different areas is necessary for
profitable sugarcane cropping. The specific objectives of this study were: a) to assess the
spectral separability of different sugarcane varieties, b) to determine which plant attributes will
provide the potential discriminating features, and c) to assess the accuracy of image
classification to map sugarcane varieties.
Using an atmospherically corrected EO-1 Hyperion image acquired over Mackay, Queensland,
Australia, the apparent reflectance signatures from sample areas of sugarcane varieties were
analysed using discriminant analysis (DA) to explore spectral separability and to determine the
optimum bands and indices. Five and eight cane varieties were separately used for each DA run.
Then, image classification was implemented for eight cane varieties using four selected
classification algorithms. These were independently performed for: a) 152 individual Hyperion
bands, and b) a selection of 20 spectral vegetation indices.
From the discriminant analysis, the classification results indicate a high discrimination between
cane varieties, i.e. 97% accuracy for five varieties and 74% for eight varieties. The best indices
for discrimination were OSAVI, TCARI, Ratio 770/550, Pigment Specific Simple Ratio
(Chlorophyll b) and Simple Ratio 800/550, indicating that pigments and the leaf internal
structure were relevant in the discrimination. However, for the classification of the entire image,
the results were not encouraging; the highest classification accuracy was only 46%. The low
accuracy can be attributed to the high number of classes used (i.e. eight cane varieties) and the
many confounding factors pertaining to crops, management regime, growth stage, and
background features such as soils. Thus, future approaches should consider the integration of
non-image information (e.g. soil information, crop calendar, etc.) and/or exploring the
usefulness of other measurable plant attributes (e.g. leaf/canopy geometry).
1. INTRODUCTION
The genetic variety of sugarcane is a major factor in many aspects of sugarcane production. It is
related to growth, yield, sugar quality, and resistance or susceptibility to pest and diseases (Bull,
2000; Cox, et al., 2000; Croft, et al., 2000; Bonnett, 1998). Variety is so central in sugarcane
cropping that the Sugarcane Industry Act 1999 of Australia requires growers to only plant and
grow those varieties covered in the “BSES Approved Variety List”. Thus, reliable information
about cane varieties is necessary in sugarcane cropping, particularly when conducting sugarcane
growth and yield prediction, or pest and disease vulnerability assessment.
While the use of remote sensing for mapping sugarcane crops has already been attempted (e.g.
Soria, et al., 2002; Hadsarang and Sukmuang, 2000; Lee-Lovick and Kirchner, 1991), its
specific application to sugarcane variety mapping has been rarely exploited. In addition, the
advent of hyperspectral sensors that can potentially discriminate subtle differences in plant bio-physical
and bio-chemical attributes has provided new opportunities (e.g. Kumar, et al., 2001).
Therefore, the aim of the study was to examine the potential of a spaceborne hyperspectral
sensor (EO-1 Hyperion) to discriminate and map sugarcane varieties. The specific objectives
were:
- to assess the spectral separability of different sugarcane varieties;
- to determine which plant attributes (e.g. leaf pigments, leaf internal structure, water
absorption, etc.) will provide the potential discriminating features for sugarcane variety
mapping; and
- to assess the accuracy of image classification to map sugarcane varieties.
This study was related to our recent work on using Hyperion data for discriminating sugarcane
“orange rust” disease (Apan, et al., 2004). We used the same study area and pre-processing
techniques for the Hyperion hyperspectral image.
