Next Article in Journal
Estimating Live Fuel Moisture Using SMAP L-Band Radiometer Soil Moisture for Southern California, USA
Next Article in Special Issue
Remote Sensing of Ice Phenology and Dynamics of Europe’s Largest Coastal Lagoon (The Curonian Lagoon)
Previous Article in Journal
Sentinel-3A SRAL Global Statistical Assessment and Cross-Calibration with Jason-3
Previous Article in Special Issue
A New Retracking Algorithm for Retrieving Sea Ice Freeboard from CryoSat-2 Radar Altimeter Data during Winter–Spring Transition
Open AccessArticle

An Optimal Decision-Tree Design Strategy and Its Application to Sea Ice Classification from SAR Imagery

1
Department of Physics and Technology, UiT The Arctic University of Norway, 9019 Tromsø, Norway
2
Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Bussestr. 24, 27570 Bremerhaven, Germany
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(13), 1574; https://doi.org/10.3390/rs11131574
Received: 10 May 2019 / Revised: 27 June 2019 / Accepted: 1 July 2019 / Published: 3 July 2019
We introduce the fully automatic design of a numerically optimized decision-tree algorithm and demonstrate its application to sea ice classification from SAR data. In the decision tree, an initial multi-class classification problem is split up into a sequence of binary problems. Each branch of the tree separates one single class from all other remaining classes, using a class-specific selected feature set. We optimize the order of classification steps and the feature sets by combining classification accuracy and sequential search algorithms, looping over all remaining features in each branch. The proposed strategy can be adapted to different types of classifiers and measures for the class separability. In this study, we use a Bayesian classifier with non-parametric kernel density estimation of the probability density functions. We test our algorithm on simulated data as well as airborne and spaceborne SAR data over sea ice. For the simulated cases, average per-class classification accuracy is improved between 0.5% and 4% compared to traditional all-at-once classification. Classification accuracy for the airborne and spaceborne SAR datasets was improved by 2.5% and 1%, respectively. In all cases, individual classes can show larger improvements up to 8%. Furthermore, the selection of individual feature sets for each single class can provide additional insights into physical interpretation of different features. The improvement in classification results comes at the cost of longer computation time, in particular during the design and training stage. The final choice of the optimal algorithm therefore depends on time constraints and application purpose. View Full-Text
Keywords: classification; decision tree; feature selection; SAR; sea ice; ice types classification; decision tree; feature selection; SAR; sea ice; ice types
Show Figures

Graphical abstract

MDPI and ACS Style

Lohse, J.; Doulgeris, A.P.; Dierking, W. An Optimal Decision-Tree Design Strategy and Its Application to Sea Ice Classification from SAR Imagery. Remote Sens. 2019, 11, 1574.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

1
Back to TopTop