Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests |
| |
| Affiliation: | 1. Departament of Forest Science, Federal University of Paraná (UFPR), Pref. Lothário Meissner Avenue 900, 80210-170 Curitiba, PR, Brazil;2. Cartographic Engineering Department, Military Institute of Engineering (IME), Praça Gen. Tibúrcio 80, 22290-270 Rio de Janeiro, RJ, Brazil;3. Embrapa Acre, Rodovia BR-364, km 14, 69900-056 Rio Branco, AC, Brazil;1. Geodetic and Geographic Information Technologies, Middle East Technical University, 06800 Ankara, Turkey;2. Astronautical Engineering Department, University of Turkish Aeronautical Association, 06797 Ankara, Turkey;3. Nature Conservation Centre, 06530 Ankara, Turkey;1. GIPSA-Lab, 11 rue des Mathématiques, 38400 Saint Martin d''Hères, France;2. Department of Global Ecology, Carnegie Institution for Science, 260 Panama Street, Stanford, CA 94305, USA;3. CESBIO, 18 avenue Edouard Belin, 31400 Toulouse, France;4. Technical University of Catalonia (UPC), Jordi Girona 1-3, edifici D5, 08034 Barcelona, Spain;5. Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavík, Iceland |
| |
| Abstract: | Remote sensing images obtained by unoccupied aircraft systems (UAS) across different seasons enabled capturing of species-specific phenological patterns of tropical trees. The application of UAS multi-season images to classify tropical tree species is still poorly understood. In this study, we used RGB images from different seasons obtained by a low-cost UAS and convolutional neural networks (CNNs) to map tree species in an Amazonian forest. Individual tree crowns (ITC) were outlined in the UAS images and identified to the species level using forest inventory data. The CNN model was trained with images obtained in February, May, August, and November. The classification accuracy in the rainy season (November and February) was higher than in the dry season (May and August). Fusing images from multiple seasons improved the average accuracy of tree species classification by up to 21.1 percentage points, reaching 90.5%. The CNN model can learn species-specific phenological characteristics that impact the classification accuracy, such as leaf fall in the dry season, which highlights its potential to discriminate species in various conditions. We produced high-quality individual tree crown maps of the species using a post-processing procedure. The combination of multi-season UAS images and CNNs has the potential to map tree species in the Amazon, providing valuable insights for forest management and conservation initiatives. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
