Remote sensing based mapping of Tillandsia fields - A semi-automatic detection approach in the hyperarid coastal Atacama Desert, northern Chile. (October 2022)

• Record Type: Journal Article
• Authors: Mikulane, Signe; Siegmund, Alexander; Río, Camilo del; Koch, Marcus A.; Osses, Pablo; García, Juan-Luis
• Is Part Of: Journal of arid environments. Volume 205(2022)
• Publication Date: 2022-10
• Subjects: Atacama desert -- Deep learning tools -- Fog ecosystem -- Remote sensing -- Tillandsia detection -- Tillandsia landbeckii; Arid regions ecology -- Periodicals; Arid regions -- Periodicals; Écologie des régions arides -- Périodiques; Régions arides -- Périodiques; 577.54
• DOI: 10.1016/j.jaridenv.2022.104821
• Languages: English
• ISSNs: 0140-1963

Abstract

Abstract: Unique fog ecosystems that occur inland along the Chilean coastal desert are dominated by Tillandsia landbeckii . The average annual precipitation in this hyperarid area lies below 1 mm per year. Tillandsia are specialized in the foliar uptake of fog as a main source of water. The detailed mapping of the distribution of Tillandsia is lacking, making it difficult to understand their geo-ecological niche and to determine the impacts that climate change may have on this species. The objective of this study is to create a detailed spatial distribution of Tillandsia in the Atacama Desert in northern Chile based on remote sensing semi-automatic detection process. For this purpose, high-resolution WorldView-3 optical satellite data has been acquired. The extraction of Tillandsia was done with ENVI Deep Learning tools. As a result, a map of Tillandsia has been created. Several fields were found between Cerro Huantajaya in the north and Cerro Soronal in the south in the study area between 800 and 1300 m a.s.l. For validation purposes ground truth data has been used. The overall accuracy of this classification is 92.02%. The results can be used as a basis for geo-ecological niche modeling, further monitoring and for the development of conservation strategies. Highlights: High resolution map of Tillandsia distribution in the Atacama Desert was created. A remote sensing-based approach has been developed, using WorldView-3 satellite data. The overall accuracy of the classification is 92.02%, based on deep learning approach. The developed workflow can be used for monitoring of Tillandsia for other regions. Results can be used as a basis for geo-ecological niche modeling of fog ecosystems.