The Special Natural Reserve of Malpaís de Güímar is a recent volcanic enclave, colonized by typical vegetation formations of the basal floor of the south of Tenerife (Canary Islands, Spain). The beekeeping that is currently carried out in this area requires a reliable mapping of the flora that conforms it. This work analyses the potential of hyperspectral images of 10 cm, captured from a UAV in June 2018, to make a preliminary thematic map of the species of interest. The study focuses on a reduced area of 6 ha, in order to assess the feasibility of the methodology and then apply it to the whole of the protected area. The results of applying a traditional algorithm to two sets of spectral bands obtained from the original 150, between 400 and 1000 nm, were compared. The first, result of a study of spectral separability and the second from the Principal Components Analysis. The best-classified species was the Cardon with an omission error of 17.70% and a commission error of 12.26%.
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%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.