Transferability of decision trees for land cover classification in a heterogeneous area
AbstractAs the value of accurate land cover becomes more apparent, methods to decrease the costs associated with supervised land cover mapping are investigated. One such method is to use training data captured in one scene and apply it to a different scene through a process known as signature extension. This paper attempts to derive classification rules from training data of four Landsat-8 scenes by using the classification and regression tree (CART) implementation of the decision tree algorithm. The transferability of the ruleset was evaluated by classifying two adjacent scenes. The classification of the four mosaicked scenes achieved an overall accuracy of 80.6%, while the two adjacent scenes achieved 61.4% and 83.7% respectively. The low accuracy of the first adjacent scene can be ascribed to a misclassification of graminoids, urban and bare areas, attributed to the temporal changes of grasslands throughout the year. In an attempt to improve the results, a normalised difference vegetation index (NDVI) threshold was applied to each scene. This increased the accuracy of the first adjacent scene but decreased the accuracy of the second. We conclude that signature extension using CART is unreliable. However, simple rules can be added to improve the results.
Authors who submit papers to this journal agree to the following terms:
a) Authors retain copyright over their work, while allowing the journal to place this work on the journal website under a Creative Commons Attribution License, which allows others to freely access, use, and share the work, with an acknowledgment of the work's authorship and its initial publication in this journal.
b) Authors are able to waive the terms of the CC license and enter into separate, additional contractual arrangements for the non-exclusive distribution and subsequent publication of this work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
c) In addition, authors are encouraged to post and share their work online (e.g., in institutional repositories or on their website) at any point after publication on the journal website.