Ghent University Academic Bibliography

Advanced

Impact of reducing polarimetric SAR input on the uncertainty of crop classifications based on the random forests algorithm

Lien Loosvelt UGent, Jan Peters UGent, Henning Skriver, Bernard De Baets UGent and Niko Verhoest UGent (2012) IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. 50(10). p.4185-4200
abstract
Although the use of multidate polarimetric synthetic aperture radar (SAR) data for highly accurate land cover classification has been acknowledged in the literature, the high dimensionality of the data set remains a major issue. This study presents two different strategies to reduce the number of features in multidate SAR data sets: an accuracy-oriented reduction and an efficiency-oriented reduction. For both strategies, the effect of feature reduction on the quality of the land cover map is assessed. The analyzed data set consists of 20 polarimetric features derived from L-band (1.25 GHz) SAR acquired by the Danish EMISAR on four dates within the period April to July in 1998. The predictive capacity of each feature is analyzed by the importance score generated by random forests (RF). Results show that according to the variation in importance score over time, a distinction can be made between general and specific features for crop classification. Based on the importance ranking, features are gradually removed from the single-date data sets in order to construct several multidate data sets with decreasing dimensionality. In the accuracy-oriented and efficiency-oriented reduction, the input is limited to eight and three features per acquisition, respectively. On the reduced input, a multidate model is built using the RF algorithm. Results indicate a decline in the classification uncertainty when feature reduction is performed.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
LAND-COVER CLASSIFICATION, ERROR, prediction probabilities, random forests, CATEGORICAL-DATA, C-BAND SAR, VARIABLE IMPORTANCE MEASURES, AGRICULTURAL CROPS, UNSUPERVISED CLASSIFICATION, PREDICTOR CORRELATION, DISTRIBUTION MODELS, FEATURE-SELECTION, polarimetric synthetic aperture radar (SAR), polarimetric features, land cover, input reduction, entropy, Classification uncertainty
journal title
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
IEEE Trans. Geosci. Remote Sensing
volume
50
issue
10
pages
4185 - 4200
Web of Science type
Article
Web of Science id
000309361700024
JCR category
ENGINEERING, ELECTRICAL & ELECTRONIC
JCR impact factor
3.467 (2012)
JCR rank
13/242 (2012)
JCR quartile
1 (2012)
ISSN
0196-2892
DOI
10.1109/TGRS.2012.2189012
language
English
UGent publication?
yes
classification
A1
copyright statement
I have transferred the copyright for this publication to the publisher
id
3050336
handle
http://hdl.handle.net/1854/LU-3050336
date created
2012-11-09 14:37:22
date last changed
2012-11-12 09:45:14
@article{3050336,
  abstract     = {Although the use of multidate polarimetric synthetic aperture radar (SAR) data for highly accurate land cover classification has been acknowledged in the literature, the high dimensionality of the data set remains a major issue. This study presents two different strategies to reduce the number of features in multidate SAR data sets: an accuracy-oriented reduction and an efficiency-oriented reduction. For both strategies, the effect of feature reduction on the quality of the land cover map is assessed. The analyzed data set consists of 20 polarimetric features derived from L-band (1.25 GHz) SAR acquired by the Danish EMISAR on four dates within the period April to July in 1998. The predictive capacity of each feature is analyzed by the importance score generated by random forests (RF). Results show that according to the variation in importance score over time, a distinction can be made between general and specific features for crop classification. Based on the importance ranking, features are gradually removed from the single-date data sets in order to construct several multidate data sets with decreasing dimensionality. In the accuracy-oriented and efficiency-oriented reduction, the input is limited to eight and three features per acquisition, respectively. On the reduced input, a multidate model is built using the RF algorithm. Results indicate a decline in the classification uncertainty when feature reduction is performed.},
  author       = {Loosvelt, Lien and Peters, Jan and Skriver, Henning and De Baets, Bernard and Verhoest, Niko},
  issn         = {0196-2892},
  journal      = {IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING},
  keyword      = {LAND-COVER CLASSIFICATION,ERROR,prediction probabilities,random forests,CATEGORICAL-DATA,C-BAND SAR,VARIABLE IMPORTANCE MEASURES,AGRICULTURAL CROPS,UNSUPERVISED CLASSIFICATION,PREDICTOR CORRELATION,DISTRIBUTION MODELS,FEATURE-SELECTION,polarimetric synthetic aperture radar (SAR),polarimetric features,land cover,input reduction,entropy,Classification uncertainty},
  language     = {eng},
  number       = {10},
  pages        = {4185--4200},
  title        = {Impact of reducing polarimetric SAR input on the uncertainty of crop classifications based on the random forests algorithm},
  url          = {http://dx.doi.org/10.1109/TGRS.2012.2189012},
  volume       = {50},
  year         = {2012},
}

Chicago
Loosvelt, Lien, Jan Peters, Henning Skriver, Bernard De Baets, and Niko Verhoest. 2012. “Impact of Reducing Polarimetric SAR Input on the Uncertainty of Crop Classifications Based on the Random Forests Algorithm.” Ieee Transactions on Geoscience and Remote Sensing 50 (10): 4185–4200.
APA
Loosvelt, L., Peters, J., Skriver, H., De Baets, B., & Verhoest, N. (2012). Impact of reducing polarimetric SAR input on the uncertainty of crop classifications based on the random forests algorithm. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 50(10), 4185–4200.
Vancouver
1.
Loosvelt L, Peters J, Skriver H, De Baets B, Verhoest N. Impact of reducing polarimetric SAR input on the uncertainty of crop classifications based on the random forests algorithm. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. 2012;50(10):4185–200.
MLA
Loosvelt, Lien, Jan Peters, Henning Skriver, et al. “Impact of Reducing Polarimetric SAR Input on the Uncertainty of Crop Classifications Based on the Random Forests Algorithm.” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 50.10 (2012): 4185–4200. Print.