RT info:eu-repo/semantics/article
T1 Assessment of oak groves conservation statuses in Natura 2000 sacs with single photon Lidar and Sentinel-2 data
A1 García Galar, Aitor
A1 Lamelas, María Teresa
A1 Domingo Ruiz, Darío
K1 Nature conservation
K1 Naturaleza - Conservación
K1 Landscape Ecology
K1 Ecología del paisaje
K1 Environnement - Gestion - Europe
K1 Medio ambiente - Países de la Unión Europea
K1 Bosques - Europa
K1 Bosques - Gestión - Europa
K1 Forest management - Europe
K1 Forests and forestry
K1 Bosques y silvicultura
K1 Forest mapping
K1 Optical radar
K1 Machine learning
K1 Aprendizaje automático
K1 Artificial intelligence
K1 Bosques - Conservación - España - Navarra
K1 LiDAR
K1 Sentinel -2
K1 3106 Ciencia Forestal
K1 3106.08 Silvicultura
K1 5902.08 Política del Medio Ambiente
K1 1203.04 Inteligencia Artificial
AB Among the main objectives of Natura 2000 Network sites management plans is monitoring their conservation status under a reasonable cost and with high temporal frequency. The aim of this study is to assess the ability of single-photon light detection and ranging (LiDAR) technology (14 points per m2) and Sentinel-2 data to classify the conservation status of oak forests in four special areas of conservation in Navarra Province (Spain) that comprise three habitats. To capture the variability of conservation status within the three habitats, we first performed a random stratified sampling based on conservation status measured in the field, canopy cover, and terrain slope and height. Thereafter, we compared two metric selection approaches, namely Kruskal–Wallis and Dunn tests, and two machine learning classification methods, random forest (RF) and support vector machine (SVM), to classify the conservation statuses using LiDAR and Sentinel-2 data. The best-fit classification model, which included only LiDAR metrics, was obtained using the random forest method, with an overall classification accuracy after validation of 83.01%, 75.51%, and 88.25% for Quercus robur (9160), Quercus pyrenaica (9230), and Quercus faginea (9240) habitats, respectively. The models include three to six LiDAR metrics, with the structural diversity indices (LiDAR height evenness index, LHEI, and LiDAR height diversity index, LHDI) and canopy cover (FCC) being the most relevant ones. The inclusion of the NDVI index from the Sentinel-2 image did not improve the classification accuracy significantly. This approach demonstrates its value for classifying and subsequently mapping conservation statuses in oak groves and other Natura 2000 Network habitat sites at a regional scale, which could serve for more effective monitoring and management of high biodiversity habitats.
PB MDPI
SN 2072-4292
YR 2023
FD 2023
LK https://uvadoc.uva.es/handle/10324/63408
UL https://uvadoc.uva.es/handle/10324/63408
LA eng
NO Remote Sensing, 2023, Vol. 15, Nº. 3, 710
NO Producción Científica
DS UVaDOC
RD 22-may-2024