Land surface identification and land cover classification of arid land in Djibouti using UAV imagery

抄録

In recent years new technologies have emerged that can be used to enhance field surveys. One of these technologies are Unmanned Aerial Vehicles (UAV), that are equipped with a camera that can take images applicable for remote sensing, and which allow collection of data in places that may be difficult to access. The study site is located in Ali Faren (42̊ 49’48” E, 11̊ 21’43”) at the Province of Arta, Djibouti, which is a hot semi-arid country with a yearly average precipitation between 50 to 200 mm and daily maximum temperatures that range from 32 to 41 degrees centigrade. The main geological characteristics found in Ali Faren are volcanic formations of early Miocene age, particularly those of Basaltic series of Dalha (lower set and upper set undifferentiated in Ali Sabieh sector) and volcanic formations of early Miocene age. In this study, a field survey was conducted using Mavic Pro (DJI) and Disko-Pro AG (Parrot) drones which are equipped with a Multi-spectral camera (Parrot Sequoia) and a fully stabilized 12 megapixel camera. Imagery acquisition was conducted over several major faults on Ali-Faren in order to observe the land cover in these sections and to identify land surface attributes that may contribute to a more accurate mapping of geological features, which will contribute in further research regarding water cycling simulations.