The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets

Laven Naidoo, Renaud Mathieu, Russell Main, Waldo Kleynhans, Konrad Wessels, Gregory P. Asner, Brigitte Leblon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

The woody component in African Savannahs provides essential ecosystem services such as fuel wood and construction timber to large populations of rural communities. Woody canopy cover (i.e. the percentage area occupied by woody canopy or CC) is a key parameter of the woody component. Synthetic Aperture Radar (SAR) is effective at assessing the woody component, because of its capacity to image within-canopy properties of the vegetation while offering an all-weather capacity to map relatively large extents of the woody component. This study compared the modelling accuracies of woody canopy cover (CC), in South African Savannahs, through the assessment of a set of modelling approaches (Linear Regression, Support Vector Machines, REPTree decision tree, Artificial Neural Network and Random Forest) with the use of X-band (TerraSAR-X), C-band (RADARSAT-2) and L-band (ALOS PALSAR) datasets. This study illustrated that the ANN, REPTree and RF non-parametric modelling algorithms were the most ideal with high CC prediction accuracies throughout the different scenarios. Results also illustrated that the acquisition of L-band data be prioritized due to the high accuracies achieved by the L-band dataset alone in comparison to the individual shorter wavelengths. The study provides promising results for developing regional savannah woody cover maps using limited LiDAR training data and SAR images.

Original languageEnglish (US)
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1049-1052
Number of pages4
ISBN (Electronic)9781479957750
DOIs
StatePublished - Nov 4 2014
Externally publishedYes
EventJoint 2014 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2014 and the 35th Canadian Symposium on Remote Sensing, CSRS 2014 - Quebec City, Canada
Duration: Jul 13 2014Jul 18 2014

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)

Conference

ConferenceJoint 2014 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2014 and the 35th Canadian Symposium on Remote Sensing, CSRS 2014
CountryCanada
CityQuebec City
Period7/13/147/18/14

Fingerprint

data mining
Synthetic aperture radar
Data mining
synthetic aperture radar
Wood fuels
canopy
Timber
Decision trees
Linear regression
Ecosystems
modeling
Support vector machines
Neural networks
Wavelength
PALSAR
ALOS
TerraSAR-X
RADARSAT
ecosystem service
artificial neural network

Keywords

  • Multi-frequency
  • Non-parametric
  • Savannahs
  • Synthetic Aperture Radar
  • Woody canopy cover

ASJC Scopus subject areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Naidoo, L., Mathieu, R., Main, R., Kleynhans, W., Wessels, K., Asner, G. P., & Leblon, B. (2014). The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets. In International Geoscience and Remote Sensing Symposium (IGARSS) (pp. 1049-1052). [6946608] (International Geoscience and Remote Sensing Symposium (IGARSS)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2014.6946608

The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets. / Naidoo, Laven; Mathieu, Renaud; Main, Russell; Kleynhans, Waldo; Wessels, Konrad; Asner, Gregory P.; Leblon, Brigitte.

International Geoscience and Remote Sensing Symposium (IGARSS). Institute of Electrical and Electronics Engineers Inc., 2014. p. 1049-1052 6946608 (International Geoscience and Remote Sensing Symposium (IGARSS)).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Naidoo, L, Mathieu, R, Main, R, Kleynhans, W, Wessels, K, Asner, GP & Leblon, B 2014, The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets. in International Geoscience and Remote Sensing Symposium (IGARSS)., 6946608, International Geoscience and Remote Sensing Symposium (IGARSS), Institute of Electrical and Electronics Engineers Inc., pp. 1049-1052, Joint 2014 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2014 and the 35th Canadian Symposium on Remote Sensing, CSRS 2014, Quebec City, Canada, 7/13/14. https://doi.org/10.1109/IGARSS.2014.6946608
Naidoo L, Mathieu R, Main R, Kleynhans W, Wessels K, Asner GP et al. The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets. In International Geoscience and Remote Sensing Symposium (IGARSS). Institute of Electrical and Electronics Engineers Inc. 2014. p. 1049-1052. 6946608. (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2014.6946608
Naidoo, Laven ; Mathieu, Renaud ; Main, Russell ; Kleynhans, Waldo ; Wessels, Konrad ; Asner, Gregory P. ; Leblon, Brigitte. / The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets. International Geoscience and Remote Sensing Symposium (IGARSS). Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1049-1052 (International Geoscience and Remote Sensing Symposium (IGARSS)).
@inproceedings{e00a4b272117418fb3a9657855485924,
title = "The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets",
abstract = "The woody component in African Savannahs provides essential ecosystem services such as fuel wood and construction timber to large populations of rural communities. Woody canopy cover (i.e. the percentage area occupied by woody canopy or CC) is a key parameter of the woody component. Synthetic Aperture Radar (SAR) is effective at assessing the woody component, because of its capacity to image within-canopy properties of the vegetation while offering an all-weather capacity to map relatively large extents of the woody component. This study compared the modelling accuracies of woody canopy cover (CC), in South African Savannahs, through the assessment of a set of modelling approaches (Linear Regression, Support Vector Machines, REPTree decision tree, Artificial Neural Network and Random Forest) with the use of X-band (TerraSAR-X), C-band (RADARSAT-2) and L-band (ALOS PALSAR) datasets. This study illustrated that the ANN, REPTree and RF non-parametric modelling algorithms were the most ideal with high CC prediction accuracies throughout the different scenarios. Results also illustrated that the acquisition of L-band data be prioritized due to the high accuracies achieved by the L-band dataset alone in comparison to the individual shorter wavelengths. The study provides promising results for developing regional savannah woody cover maps using limited LiDAR training data and SAR images.",
keywords = "Multi-frequency, Non-parametric, Savannahs, Synthetic Aperture Radar, Woody canopy cover",
author = "Laven Naidoo and Renaud Mathieu and Russell Main and Waldo Kleynhans and Konrad Wessels and Asner, {Gregory P.} and Brigitte Leblon",
year = "2014",
month = "11",
day = "4",
doi = "10.1109/IGARSS.2014.6946608",
language = "English (US)",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1049--1052",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",

}

TY - GEN

T1 - The assessment of data mining algorithms for modelling Savannah Woody cover using multi-frequency (X-, C- and L-band) synthetic aperture radar (SAR) datasets

AU - Naidoo, Laven

AU - Mathieu, Renaud

AU - Main, Russell

AU - Kleynhans, Waldo

AU - Wessels, Konrad

AU - Asner, Gregory P.

AU - Leblon, Brigitte

PY - 2014/11/4

Y1 - 2014/11/4

N2 - The woody component in African Savannahs provides essential ecosystem services such as fuel wood and construction timber to large populations of rural communities. Woody canopy cover (i.e. the percentage area occupied by woody canopy or CC) is a key parameter of the woody component. Synthetic Aperture Radar (SAR) is effective at assessing the woody component, because of its capacity to image within-canopy properties of the vegetation while offering an all-weather capacity to map relatively large extents of the woody component. This study compared the modelling accuracies of woody canopy cover (CC), in South African Savannahs, through the assessment of a set of modelling approaches (Linear Regression, Support Vector Machines, REPTree decision tree, Artificial Neural Network and Random Forest) with the use of X-band (TerraSAR-X), C-band (RADARSAT-2) and L-band (ALOS PALSAR) datasets. This study illustrated that the ANN, REPTree and RF non-parametric modelling algorithms were the most ideal with high CC prediction accuracies throughout the different scenarios. Results also illustrated that the acquisition of L-band data be prioritized due to the high accuracies achieved by the L-band dataset alone in comparison to the individual shorter wavelengths. The study provides promising results for developing regional savannah woody cover maps using limited LiDAR training data and SAR images.

AB - The woody component in African Savannahs provides essential ecosystem services such as fuel wood and construction timber to large populations of rural communities. Woody canopy cover (i.e. the percentage area occupied by woody canopy or CC) is a key parameter of the woody component. Synthetic Aperture Radar (SAR) is effective at assessing the woody component, because of its capacity to image within-canopy properties of the vegetation while offering an all-weather capacity to map relatively large extents of the woody component. This study compared the modelling accuracies of woody canopy cover (CC), in South African Savannahs, through the assessment of a set of modelling approaches (Linear Regression, Support Vector Machines, REPTree decision tree, Artificial Neural Network and Random Forest) with the use of X-band (TerraSAR-X), C-band (RADARSAT-2) and L-band (ALOS PALSAR) datasets. This study illustrated that the ANN, REPTree and RF non-parametric modelling algorithms were the most ideal with high CC prediction accuracies throughout the different scenarios. Results also illustrated that the acquisition of L-band data be prioritized due to the high accuracies achieved by the L-band dataset alone in comparison to the individual shorter wavelengths. The study provides promising results for developing regional savannah woody cover maps using limited LiDAR training data and SAR images.

KW - Multi-frequency

KW - Non-parametric

KW - Savannahs

KW - Synthetic Aperture Radar

KW - Woody canopy cover

UR - http://www.scopus.com/inward/record.url?scp=84911392454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911392454&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2014.6946608

DO - 10.1109/IGARSS.2014.6946608

M3 - Conference contribution

AN - SCOPUS:84911392454

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1049

EP - 1052

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

PB - Institute of Electrical and Electronics Engineers Inc.

ER -