Articles | Volume 21, issue 11
https://doi.org/10.5194/bg-21-2909-2024
https://doi.org/10.5194/bg-21-2909-2024
Research article
 | 
14 Jun 2024
Research article |  | 14 Jun 2024

From simple labels to semantic image segmentation: leveraging citizen science plant photographs for tree species mapping in drone imagery

Salim Soltani, Olga Ferlian, Nico Eisenhauer, Hannes Feilhauer, and Teja Kattenborn

Related authors

Crowd-sourced trait data can be used to delimit global biomes
Simon Scheiter, Sophie Wolf, and Teja Kattenborn
EGUsphere, https://doi.org/10.5194/egusphere-2024-276,https://doi.org/10.5194/egusphere-2024-276, 2024
Short summary

Related subject area

Biodiversity and Ecosystem Function: Terrestrial
Plant functional traits modulate the effects of soil acidification on above- and belowground biomass
Xue Feng, Ruzhen Wang, Tianpeng Li, Jiangping Cai, Heyong Liu, Hui Li, and Yong Jiang
Biogeosciences, 21, 2641–2653, https://doi.org/10.5194/bg-21-2641-2024,https://doi.org/10.5194/bg-21-2641-2024, 2024
Short summary
Regional effects and local climate jointly shape the global distribution of sexual systems in woody flowering plants
Minhua Zhang, Xiaoqing Hu, and Fangliang He
Biogeosciences, 21, 2133–2142, https://doi.org/10.5194/bg-21-2133-2024,https://doi.org/10.5194/bg-21-2133-2024, 2024
Short summary
Ideas and perspectives: Sensing energy and matter fluxes in a biota-dominated Patagonian landscape through environmental seismology – introducing the Pumalín Critical Zone Observatory
Christian H. Mohr, Michael Dietze, Violeta Tolorza, Erwin Gonzalez, Benjamin Sotomayor, Andres Iroume, Sten Gilfert, and Frieder Tautz
Biogeosciences, 21, 1583–1599, https://doi.org/10.5194/bg-21-1583-2024,https://doi.org/10.5194/bg-21-1583-2024, 2024
Short summary
Comparison of carbon and water fluxes and the drivers of ecosystem water use efficiency in a temperate rainforest and a peatland in southern South America
Jorge F. Perez-Quezada, David Trejo, Javier Lopatin, David Aguilera, Bruce Osborne, Mauricio Galleguillos, Luca Zattera, Juan L. Celis-Diez, and Juan J. Armesto
Biogeosciences, 21, 1371–1389, https://doi.org/10.5194/bg-21-1371-2024,https://doi.org/10.5194/bg-21-1371-2024, 2024
Short summary
Kilometre-scale simulations over Fennoscandia reveal a large loss of tundra due to climate warming
Fredrik Lagergren, Robert G. Björk, Camilla Andersson, Danijel Belušić, Mats P. Björkman, Erik Kjellström, Petter Lind, David Lindstedt, Tinja Olenius, Håkan Pleijel, Gunhild Rosqvist, and Paul A. Miller
Biogeosciences, 21, 1093–1116, https://doi.org/10.5194/bg-21-1093-2024,https://doi.org/10.5194/bg-21-1093-2024, 2024
Short summary

Cited articles

Affouard, A., Goëau, H., Bonnet, P., Lombardo, J.-C., and Joly, A.: Pl@ntnet app in the era of deep learning, in: ICLR: International Conference on Learning Representations, April 2017, Toulon, France, ffhal-01629195f, 2017. a, b
Bayraktar, E., Basarkan, M. E., and Celebi, N.: A low-cost UAV framework towards ornamental plant detection and counting in the wild, ISPRS J. Photogramm., 167, 1–11, https://doi.org/10.1016/j.isprsjprs.2020.06.012, 2020. a
Boone, M. E. and Basille, M.: Using iNaturalist to contribute your nature observations to science, EDIS, 2019, 5–5, 2019. a, b, c
Bouguettaya, A., Zarzour, H., Kechida, A., and Taberkit, A. M.: Deep learning techniques to classify agricultural crops through UAV imagery: A review, Neural Comput. Appl., 34, 9511–9536, 2022. a
Braga, G., J. R., Peripato, V., Dalagnol, R., P. Ferreira, M., Tarabalka, Y., OC Aragão, L. E., F. de Campos Velho, H., Shiguemori, E. H., and Wagner, F. H.: Tree crown delineation algorithm based on a convolutional neural network, Remote Sens., 12, 1288, https://doi.org/10.3390/rs12081288, 2020. a
Download
Short summary
In this research, we developed a novel method using citizen science data as alternative training data for computer vision models to map plant species in unoccupied aerial vehicle (UAV) images. We use citizen science plant photographs to train models and apply them to UAV images. We tested our approach on UAV images of a test site with 10 different tree species, yielding accurate results. This research shows the potential of citizen science data to advance our ability to monitor plant species.
Altmetrics
Final-revised paper
Preprint