Urban forest analysis: species classification using machine learning and remote sensing data
https://doi.org/10.18303/2619-1563-2023-4-36
Abstract
Effective management of urban forests requires an integrated approach, starting with a complete inventory of their biodiversity. At the moment, data on the floristic composition of urban forests in Siberian cities is either limited or fragmentary. The purpose of this study is to classify urban forests by species and determine their ontogenetic state using remote sensing materials. This study aims to deeply analyze the structure of urban forests using remote sensing data, in particular the use of unmanned aerial vehicles.
About the Authors
M. V. Platonova
Novosibirsk State University
Russian Federation
Russian Federation
Pirogova Str., 1, Novosibirsk, 630090, Russia
A. V. Kukharskii
Novosibirsk State University
Russian Federation
Russian Federation
Pirogova Str., 1, Novosibirsk, 630090, Russia
E. B. Talovskaya
Novosibirsk State University;
Central Siberian Botanical Garden of the Siberian Branch of the Russian Academy of Sciences
Russian Federation
Russian Federation
Pirogova Str., 1, Novosibirsk, 630090, Russia;
Central Siberian Botanical Garden of the Siberian Branch of the Russian Academy of Sciences
G. I. Lazorenko
Novosibirsk State University
Russian Federation
Russian Federation
Pirogova Str., 1, Novosibirsk, 630090, Russia
References
1. Chen T., Guestrin C. Xgboost: A scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. – 2016. – P. 785–794, doi: 10.1145/2939672.2939785.
2. Chistyakova A.A. Ontogenesis of Betula pendula Roth. Diagnosis and keys of age condition of forest plants // Trees and bushes [in Russian]. – Prometei, Moscow, 1989. – P. 89–96.
3. Cunliffe A.M., Assmann J.J., Daskalova G.N., Kerby J.T., Myers-Smith I.H. Aboveground biomass corresponds strongly with drone-derived canopy height but weakly with greenness (NDVI) in a shrub tundra landscape // Environmental Research Letters. – 2020. – Vol. 15. – Article 125004, doi: 10.1088/1748-9326/aba470.
4. Huang S., Tang L., Hupy J.P., Wang Y., Shao G. A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing // Journal of Forestry Research. – 2021. – Vol. 32 (5). – P. 1–6, doi: 10.1007/s11676-020-01155-1.
5. Johnston C.M.T., Withey P. Managing forests for carbon and timber: a Markov decision model of uneven-aged forest management with risk // Ecological Economics. – 2017. – Vol. 138. – P. 31–39, doi: 10.1016/j.ecolecon.2017.03.023.
6. Ontl T.A., Janowiak M.K., Swanston C.W., Daley J., Handler S., Cornett M., Hagenbuch S., Handrick C., McCarthy L., Patch N. Forest management for carbon sequestration // Journal of Forestry. – 2020. – Vol. 118 (1). – P. 86–101, doi: 10.1093/jofore/fvz062.
7. Rabotnov T.A. Life cycle of perennial grasses in meadow coenosises // Proceedings BIN AN SSSR [in Russian]. – Moscow, Leningrad, 1950. – Vol. 6. – P. 179–196.
8. Zeng J., Matsunaga T., Tan Z.-H., Saigusa N., Shirai T., Tang Y., Peng S., Fukuda Y. Global terrestrial carbon fluxes of 1999–2019 estimated by upscaling eddy covariance data with a random forest // Scientific Data. – 2020. – Vol. 7 (1). – Article 313, doi: 10.1038/s41597-020-00653-5.
9. Zhukova L.A. Ontogenesis of Pinus sylvestris L. Ontogenetic atlas of plants [in Russian]. – Yoshkar-Ola, 2013. – Vol. 7. – P. 26–65.
Review
For citations:
Platonova M.V., Kukharskii A.V., Talovskaya E.B., Lazorenko G.I. Urban forest analysis: species classification using machine learning and remote sensing data. Russian Journal of Geophysical Technologies. 2023;(4):36-44. (In Russ.) https://doi.org/10.18303/2619-1563-2023-4-36
Views:
575
Email this article 