Translator Disclaimer
2 November 2017 Multitemporal WorldView satellites imagery for mapping chestnut trees
Author Affiliations +
Chestnuts have been part of the landscape and popular culture of the Canary Islands (Spain) since the sixteenth century. Many crops of this species are in state of abandonment and an updated mapping for its study and evaluation is needed. This work proposes the elaboration of this cartography using two satellite images of very high spatial resolution captured on two different dates and representing well-differentiated phenological states of the chestnut: a WorldView-2 image of March 10th, 2015 and a WorldView-3 image of May 12th, 2015 (without and with leaves respectively). Two study areas were selected within the municipality of La Orotava (Tenerife Island). One of the areas contains chestnut trees dispersed in an agricultural and semi-urban environment and in the other one, the specimens are grouped forming a forest merged with Canarian pines and other species of Monteverde. The Maximum Likelihood (ML), the Artificial Neural Networks (ANN) and the Spectral Angle Mapper (SAM) classification algorithms were applied to the multi-temporal image resulting from the combination of both dates. The results show the benefits of using the multi-temporal image for Pinolere with the ANN algorithm and for Chasna area with ML algorithm, in both cases providing an overall accuracy close to 95%.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
F. Marchetti, M. Arbelo, J. A. Moreno-Ruíz, P. A. Hernández-Leal, and A. Alonso-Benito "Multitemporal WorldView satellites imagery for mapping chestnut trees", Proc. SPIE 10421, Remote Sensing for Agriculture, Ecosystems, and Hydrology XIX, 104211Q (2 November 2017);

Back to Top