RT info:eu-repo/semantics/article
T1 Mapping Chestnut Stands Using Bi-Temporal VHR Data
A1 Arbelo Pérez, Manuel Imeldo
A1 Marchetti, Francesca
A1 Waske, Björn
A1 Moreno-Ruíz, Jose A.
A1 Alonso Benito, Alfonso
A2 Física
K1 WorldView
K1 bi-temporal image
K1 extended morphological profiles
K1 random forest
K1 Canary Islands
AB This study analyzes the potential of very high resolution (VHR) remote sensing images andextended morphological profiles for mapping Chestnut stands on Tenerife Island (Canary Islands,Spain). Regarding their relevance for ecosystem services in the region (cultural and provisioningservices) the public sector demand up-to-date information on chestnut and a simple straight-forwardapproach is presented in this study. We used two VHR WorldView images (March and May2015) to cover di erent phenological phases. Moreover, we included spatial information in theclassification process by extended morphological profiles (EMPs). Random forest is used for theclassification process and we analyzed the impact of the bi-temporal information as well as of thespatial information on the classification accuracies. The detailed accuracy assessment clearly revealsthe benefit of bi-temporal VHRWorldView images and spatial information, derived by EMPs, in termsof the mapping accuracy. The bi-temporal classification outperforms or at least performs equally wellwhen compared to the classification accuracies achieved by the mono-temporal data. The inclusionof spatial information by EMPs further increases the classification accuracy by 5% and reduces thequantity and allocation disagreements on the final map. Overall the new proposed classificationstrategy proves useful for mapping chestnut stands in a heterogeneous and complex landscape, suchas the municipality of La Orotava, Tenerife.
YR 2019
FD 2019
LK http://riull.ull.es/xmlui/handle/915/36910
UL http://riull.ull.es/xmlui/handle/915/36910
LA en
NO https://doi.org/10.3390/rs11212560
DS Repositorio institucional de la Universidad de La Laguna
RD 22-dic-2024