TY - JOUR
T1 - Random Forests as a tool for estimating uncertainty at pixel-level in SAR image classification
AU - Loosvelt, Lien
AU - Peters, Jan
AU - Skriver, Henning
AU - Lievens, Hans
AU - Van Coillie, Frieke M.B.
AU - De Baets, Bernard
AU - Verhoest, Niko E.C.
PY - 2012
Y1 - 2012
N2 - It is widely acknowledged that model inputs can cause considerable errors in the model output. Since land cover maps obtained from the classification of remote sensing data are frequently used as input to spatially explicit environmental models, it is important to provide information regarding the classification quality of the produced map. Map quality is generally assessed at the global or class-specific level, using standard methods based on the confusion matrix. Unfortunately, these accuracy measures do not provide information regarding the spatial variability in classification quality. In this paper, we introduce Random Forests for the probabilistic mapping of vegetation from high-dimensional remote sensing data and present a comprehensive methodology to assess and analyze classification uncertainty based on the local probabilities of class membership. We apply this method to SAR image data in order to investigate whether multi-configuration in the dataset decreases the local uncertainty estimates. Polarimetric L- and C-band EMISAR data, acquired in April, May, June and July of 1998, and covering the agricultural Foulum test site in Denmark, are used. Results show that multi-configuration in the dataset decreases the classification uncertainty for the different agricultural crops as compared to the single-configuration alternative. Furthermore, the uncertainty assessment reveals lower confidence for the classification of (mixed) pixels at the field edges, and for some fields an uncertainty pattern is observed which is hypothesized to be caused by field preparation practices and cropping system. This study demonstrates that uncertainty assessment provides valuable information on the performance of land cover classification models, both in space and time. Moreover, uncertainty estimates can be easily assessed when using the Random Forests algorithm.
AB - It is widely acknowledged that model inputs can cause considerable errors in the model output. Since land cover maps obtained from the classification of remote sensing data are frequently used as input to spatially explicit environmental models, it is important to provide information regarding the classification quality of the produced map. Map quality is generally assessed at the global or class-specific level, using standard methods based on the confusion matrix. Unfortunately, these accuracy measures do not provide information regarding the spatial variability in classification quality. In this paper, we introduce Random Forests for the probabilistic mapping of vegetation from high-dimensional remote sensing data and present a comprehensive methodology to assess and analyze classification uncertainty based on the local probabilities of class membership. We apply this method to SAR image data in order to investigate whether multi-configuration in the dataset decreases the local uncertainty estimates. Polarimetric L- and C-band EMISAR data, acquired in April, May, June and July of 1998, and covering the agricultural Foulum test site in Denmark, are used. Results show that multi-configuration in the dataset decreases the classification uncertainty for the different agricultural crops as compared to the single-configuration alternative. Furthermore, the uncertainty assessment reveals lower confidence for the classification of (mixed) pixels at the field edges, and for some fields an uncertainty pattern is observed which is hypothesized to be caused by field preparation practices and cropping system. This study demonstrates that uncertainty assessment provides valuable information on the performance of land cover classification models, both in space and time. Moreover, uncertainty estimates can be easily assessed when using the Random Forests algorithm.
KW - Synthetic aperture radar (SAR)
KW - Random Forests
KW - Multi-frequency
KW - Multi-date
KW - Land cover
KW - Crop classification
KW - Model uncertainty
KW - Prediction probability
KW - Data fusion
KW - Entropy
U2 - 10.1016/j.jag.2012.05.011
DO - 10.1016/j.jag.2012.05.011
M3 - Journal article
SN - 0303-2434
VL - 19
SP - 173
EP - 184
JO - International Journal of Applied Earth Observation and Geoinformation
JF - International Journal of Applied Earth Observation and Geoinformation
ER -