Land cover classification using high‐resolution aerial photography in adventdalen, svalbard

Abstract

A methodology was tested for high‐resolution mapping of vegetation and detailed geoecological patterns in the Arctic Tundra, based on aerial imagery from an unmanned aerial vehicle (visible wavelength – RGB, 6 cm pixel resolution) and from an aircraft (visible and near infrared, 20 cm pixel resolution). The scenes were fused at 10 and 20 cm to evaluate their applicability for vegetation mapping in an alluvial fan in dventdalen, Svalbard. Ground‐truthing was used to create training and accuracy evaluation sets. Supervised classification tests were conducted with different band sets, including the original and derived ones, such as and principal component analysis bands. The fusion of all original bands at 10 cm resolution provided the best accuracies. The best classifier was systematically the maximum neighbourhood algorithm, with overall accuracies up to 84%. Mapped vegetation patterns reflect geoecological conditioning factors. The main limitation in the classification was differentiating between the classes graminea, moss and Salix, and moss, graminea and Salix, which showed spectral signature mixing. Silty‐clay surfaces are probably overestimated in the south part of the study area due to microscale shadowing effects. The results distinguished vegetation zones according to a general gradient of ecological limiting factors and show that + high‐resolution imagery are excellent tools for identifying the main vegetation groups within the lowland fan study site of dventdalen, but do not allow for detailed discrimination between species.

Key words:

• high‐resolution remote sensing
• near infrared
• UAV
• vegetation
• Svalbard

Acknowledgements

This research has been conducted in the framework of project ANAPOLIS (PTDC/CTE‐SPA/99041/2008) funded by the Fundação para a Ciência e a Tecnologia. The activities are framed within the Portuguese Polar Program (PROPOLAR). Maura Lousada benefited from a CGD Mobility Grant from the New Generation of Polar Scientists Program and from working in Svalbard as a UNIS masters student. UNIS supported logistics in Svalbard. The UAV imagery was obtained by Kolibri Geo Services. The digital aerial orthophotos were obtained by the Norwegian Polar Institute. We thank the Associate Editor, as well as Dr Hans Tømmervik and two other anonymous reviewers for their numerous comments and suggestions, which contributed to significantly improve the original manuscript.

Additional information

Notes on contributors

Carla Mora

Carla Mora, Gonçalo Vieira, CEG/IGOT, University of Lisbon, Edifício FLUL, Alameda da Universidade, 1600‐214 Lisboa, Portugal.

E‐mail: [email protected]

Pedro Pina

Pedro Pina, Maura Lousada, CERENA‐IST, University of Lisbon, Instituto Superior Técnico, Av. Rovisco Pais, 1049‐001 Lisboa, Portugal

Hanne H. Christiansen

Hanne H. Christiansen, Geology Department, The University Centre in Svalbard, UNIS, P.O. Box 156N‐9171 Longyearbyen, Norway