Abstract. The purpose of the study is to rank woody areas of different lengths within the forest biogeocenosis based on remote sensing data and using artificial intelligence. Materials and methods. The object of the study is the “Bely Klyuch” natural landmark of the Tatishchevsky district of the Saratov region. The research materials are multichannel satellite images in the visible and near-infrared spectral ranges. The processing of materials and their mapping were completed using the cross-platform QGIS system (version 3.28.0). Recognition of biogeocenosis objects was carried out using the Mapflow plugin. Results. A multilevel structure of the biogeocenosis has been established. It was found that 60–65 % of woody areas belong to the high forest, and 30–35 % to the medium forest. Signs of sustainable development of the deciduous forest biogeocenosis have been established: indistinctness of the soil line in the coordinates of greenness vs brightness, NIR–RED tasseled cap transformations; high dispersion of dependencies wetness vs brightness; greenness vs wetness; the presence of a local area at the top of the principal component diagrams, in which their values vary over a wide range; asymmetry and skewness towards higher values of frequency diagrams of wetness and greenness, as well as the EVI index. Discussion. For forested areas, the structure of the tasseled cap diagrams is characterized by indistinct and blurred soil line, as well as by a concentration of maximum vegetation component in certain areas. The reason for this is that in forests, unlike agricultural lands, the soil is hidden under a layer of foliage, fallen leaves, and moss; therefore, the reflected signal from the soil mixes with the reflection from the vegetation. The predominance of high forest indicates that the upper layer of the biogeocenosis occupies a large part of the territory and is a determining factor in the structure and functioning of the ecosystem. Tall trees create shade, influence the microclimate, soil conditions, and light availability for the lower layers.

For citation: Kosarev A.V., Sergeeva I.V., Klyuchikov A.V., Chumakova S.V., Leontiev A.A. Characteristics of the woody vegetation of the forest biogeocenosis using artificial intelligence based on remote sensing data. Geosistemy perehodnykh zon = Geosystems of Transition Zones, 2025, vol. 9, No. 3, pp. 286–298. (In Russ.).
https://doi.org/10.30730/gtrz.2025.9.3.286-298, https://www.elibrary.ru/fvkynr

Для цитирования: Косарев А.В., Сергеева И.В., Ключиков А.В., Чумакова С.В., Леонтьев А.А. Характеристика древесной растительности лесного биогеоценоза с применением искусственного интеллекта на основе данных дистанционного зондирования. Геосистемы переходных зон, 2025, т. 9, № 3, с. 286–298.
https://doi.org/10.30730/gtrz.2025.9.3.286-298, https://www.elibrary.ru/fvkynr

1. Sushkevich T.A., Strelkov S.A., Maksakova S.V. 2018. Space, Earth and supercomputing: Conjugate problems of ecology, climate, monitoring and remote sensing of Earth, hyper-spectral approach and nanodiagnostics of natural environments (Dedicated to the 65th anniversary of the Keldysh Institute of Applied Mathematics of Russian Academy of Sciences). Bulletin of the South Ural State University. Series: Computational Mathematics and Software Engineering, 7(4): 5–29. (In Russ.) doi:10.14529/cmse180401

2. Zenkov I., Kustikova E., Le Hung Ch., Silvanovich O., Yuronen Yu., Maglinets Yu., Raevich K., Gerasimova E., Mironova Zh., Skornyakova S. 2024. The digital platform for resolving problems of ecology of disturbed lands for mining companies with open-pit mining based on remote sensing resources and artificial intelligence. Ecology and Industry of Russia, 28(1): 52–57. (In Russ.). https://doi.org/10.18412/1816-0395-2024-1-52-57

3. Karimullah A., Bratkov V.V. 2024. Evaluation of changes in the urban green space area of Kabul, Afganistan. Monitoring. Science and Technologies, 4(62): 59–67. (In Russ.). doi:10.25714/MNT.2024.62.008

4. Bissenbayeva S., Melisbek Sh., Baymukan Er. 2024. An overview of forest monitoring in Kazakhstan based on Earth observation. Bulletin of the L.N. Gumilyov Eurasian National University. Chemistry. Geography. Ecology Series, 147(2): 135–149. (In Russ.). https://doi.org/10.32523/2616-6771-2024-147-2-135-149

5. Danilin I.M., Lapko V.A., Kuznetsov A.A., Babiy I.A., Vaisman A.O. 2024. Innovative educational and research center for monitoring forest resources of Siberia based on laser and microwave aerospace imaging. Siberian Aerospace Journal, 25(1): 8–17. https://doi.org/10.31772/2712-8970-2024-25-1-8-17

6. Strekalovskaya M.I., Dobrotvorskaya N.I. 2023. Using GIS technologies to create a reforestation database. Interexpo GEO-Siberia, 4(2): 199–204. (In Russ). doi:10.33764/2618-981X-2023-4-2-199-204

7. Yaparov I.M., Vildanov I.R., Bashirova E., Gumerov R.A., Magasumov T.M. 2020. Analysis of multi-year dynamics of the NDVI growing index in the Iremel Natural Park for local forest management using digital terrain models. Astrakhan Bulletin of Ecological Education, 3(57): 140–149. (In Russ). https://doi.org/10.36698/2304-5957-2020-19-3-140-149

8. Mamedaliyeva V.M. 2021. Algorithm and measurement of forest cover area change in the Khachmaz region of Azerbaijan by satellite monitoring. Lesnoy Zhurnal = Russian Forestry Journal, 2(380): 106–115. (In Russ). https://doi.org/10.37482/0536-1036-2021-2-106-115

9. Chertkova E.P., Zamolodchikov D.G. 2024. Assessment of land resources of the Altai State Nature Biosphere Reserve considering the uniqueness of biodiversity and the value of ecosystems. Ecosystems, 40: 39–49. (In Russ). doi:10.29039/2413-1733-2024-40-39-49

10. Gopp N.V., Meshalkina J.L., Narykova A.N., Plotnikova A.S., Chernova O.V. 2023. Mapping of soil organic carbon content and stocks at the regional and local levels: the analysis of modern methodological approaches. Forest Science Issues, 6(4): 1–46. https://doi.org/10.31509/2658-607x-202361-120

11. Kalinicheva S.V., Nikiforova N.N., Maksimov N.A., Misailov I.E., Fedorov A.N. 2021. Investigation of the forest attack on the tundra in the Eastern Siberia region in a changing climate using GIS and Earth remote sensing data. Vestnik Severo-Vostocnogo federal?nogo universiteta imeni M.K. Ammosova. Seria: Nauki o Zemle, 4(24): 73–82. (In Russ.). doi:10.25587/SVFU.2021.24.4.017

12. Alekseev A.S., Chernikhovskiy D.M. 2024. Identification of damage to coniferous stands based on comprehensive analysis of the results of remote sensing of the Earth and ground surveys. Lesnoy Zhurnal = Russian Forestry Journal, 2: 11–28. (In Russ.). https://doi.org/10.37482/0536-1036-2024-2-11-28

13. Bespalova V.V., Polyanskaya O.A. 2021. Implementation of digital technologies at the enterprises of the forest complex. Journal of Applied Research, 2(4): 66–70. (In Russ.). doi:10.47576/2712-7516_2021_2_4_66

14. Ivanova N.V., Shashkov М.P., Lebedev А.V., Shanin V.N. 2024. Quantitative analysis of factors influencing damage to old-growth hemiboreal stands as a result of a catastrophic windthrow, based on remote sensing and merged data. Ekologiya, 4: 284–292. (In Russ.). https://doi.org/10.31857/S0367059724040043

15. Linkina A.V., Elsukov V.D., Trishin A.A. 2023. The use of machine learning models in solving problems in the field of organic agriculture. Proceedings of the Voronezh State University of Engineering Technologies, 85(4): 133–138. (In Russ.). https://doi.org/10.20914/2310-1202-2023-4-133-138

16. Nikolaev A.A., Nikolaeva I.O. 2022. [Transformation of digital satellite imagery data by the tasseled cap algorithm in determining the structure of forest plantations]. Mezhdunarodnyy nauchno-issledovatel'skiy zhurnal =International Research Journal, 9(123): 1–5. (In Russ.). doi:10.23670/IRJ.2022.123.77;
URL: https://research-journal.org/archive/9-123-2022-september/10.23670/IRJ.2022.123.77 (accessed 20.04.2025).