Typology assessment of hunting grounds of key ornithological territory «Lake Il'men and adjoining marshy plain» using remote sensing data and GIS-technologies

Earth remote sensing data and GIS technology now provide a large amount of reliable information on the state of natural and man-made landscapes. Hunting resources and habitat are based on such landscapes and closely interrelated; the species composition and number of hunting resources depend to a large extent on the distribution of their habitat elements within the hunting grounds. A number of normative documents of the Russian Federation regulating the management of hunting and hunting activities reflect the fact that the most effective is inventoring the current state of the habitat of hunting animals on a single methodological basis, including monitoring using and analysing data from remote sensing of the Earth’s surface and aerial photography of hunting landscapes. The aim of this study was to develop an approach to typology classification of habitat elements of hunting resources based on the application of remote sensing data from the Earth (aerial photography with unmanned aircraft and space im-agery with Sentinel-2A), forest management materials, semi-automatic image classification algorithms and geo-information analysis of the resulting data. The study was conducted on a key ornithological area of international importance (KOA) NV-005 «Lake Il'men and adjoining marshy plain» with a total area of 190,950 ha, located in the Novgorod region. The software tools for data processing and analysis were QGis, a plugin of automated classification of images dzetsaka: classification tool with Pythonlibrary scikit-learn; “random forest” classification algorithm has been applied. As a result of this work, the schematic map of the habitat elements of hunting resources KOA NV-005 «Lake Il'men and adjoining marshy plain» and an attribute table with the distribution of the area of habitat elements of hunting resources according to the current regulatory requirements of regional hunting were formed. The accuracy of the automated classification and the reliability of the results obtained were assessed by using a built-in error matrix and Cohen’s Kappa coefficient calculation. The proposed approach can be effectively applied not only in hunting practices, but also in the monitoring of natural and human landscapes that include different land categories.

1. Breiman L. Random Forests. Machine Learning, 2001, vol. 45, pp. 5–32.

2. Cherekaev A.V., Safonov V.G., Andreev M.N., Grakov N.N., Domskiy I.A., Kraev N.V., Matveychuk S.P., Mashkin V.I., Minkov S.I. Kontseptsiya razvitiya i nauchnogo obespecheniya ohotnich'ego hozyajstva Rossii. Trudy VNIIOZ, 2000, no. 1(51), pp. 7– 16. DOI: 10.5281/zenodo.11080398. (In Russ.)

3. Dergunov D.M., Vorob'yov O.N., Kurbanov E.A., Lezhnin S.A., Gubaev A.V. Otsenka algoritma «Sluchajnyj les» mashinnogo obucheniya dlya klassifikatsii fitomassy lesov. Vestnik Povolzhskogo gosudarstvennogo tekhnologicheskogo universiteta. Ser.: Les. Ekologiya. Prirodopol'zovanie, 2024, no. 1 (61), pp. 30–44. (In Russ.)

4. Geograficheskie informacionnye sistemy i distancionnoe zondirovanie. URL: https://gis-lab.info/ (accessed February 21, 2024). (In Russ.)

5. Github confusion matrix. URL: https://github.com/confusion_matrix.py (accessed February 21, 2024).

6. Github dzetsaka:. URL: https://github.com/dzetsaka.py (accessed February 21, 2024).

7. Kamennova I.E. Rukovodstvo po Ramsarskoj konventsii: Spravochnik po osushchestvleniyu Konventsii o vodno-bolotnyh ugod'yah (Ramsar, Iran, 1971 g.). 4th ed. Gland: Sekretariat Ramsarskoj konventsii, 2006. 133 p. (In Russ.)

8. LVPC Novgorodskoj oblasti:. URL: https://hcvf.ru/ru/maps/hcvf-novgorod (accessed February 20, 2024). (In Russ.)

9. Malysheva N.V. Avtomatizirovannoe deshifrirovanie aerokosmicheskih izobrazhenij lesnyh nasazhdenij: uchebnoe posobie. Moscow: Izd-vo Moskovskogo gos. un-ta lesa, 2012. 151 p. (In Russ.)

10. Mishchenko A.L. Ozero Il'men' i del'ty rek Msta, Lovat' i Shelon'. Vodnobolotnye ugod'ya Rossii. T.3. Vodno-bolotnye ugod'ya, vnesennye v Perspektivnyj spisok Ramsarskoj konventsii / pod obshch. red. V.G. Krivenko. Moscow, 2000, pp. 86–88. (In Russ.)

11. Nekhajchik V.P. Razvitie i preobrazovanie geograficheskoj sredy: po materialam Novgorodskoj oblasti: sbornik nauchnyh trudov. Leningrad: LGPI im. A.I. Gertsena, 1975. 160 p. (In Russ.)

12. Pan Xin, Zhang Ce, Xu Jun, Zhao Jian. Simplified object-based deep neural network for very high resolution remote sensing image classification, ISPRS Journal of Photogrammetry and Remote Sensing, 2021, vol. 181, pp. 218–237. DOI: 10.1016/j.isprsjprs.2021.09.014.

13. Ratsional'noe prirodopol'zovanie: teoriya, praktika, obrazovanie / pod obshch. red. prof. M.V. Slipenchuka. Moscow: Geograficheskij fakul'tet MGU, 2012. 264 p. (In Russ.)

14. Scikit-learn Machine Learning in Python: [Electronic resource]. URL: https://scikit-learn.org/stable/ (accessed February 21, 2024)

15. Shihov A.N., Gerasimov A.P., Ponomarchuk A.I., Perminova E.S. Tematicheskoe deshifrirovanie i interpretatsiya kosmicheskih snimkov srednego i vysokogo prostranstvennogo razresheniya: ucheb. posobie. Perm', 2020. 191 p. (In Russ.)

16. Sidorova V.S. Sravnenie kart po kappe Koena. Interekspo Geo-Sibir', 2017, T. 4, no. 2, pp. 18–22. (In Russ.)

17. Suhomirov G.I. O problemah ohotnich'ego hozyajstva Rossii. Klimat, ekologiya, sel'skoe hozyajstvo Evrazii. Sovremennye problemy ohotovedeniya: materialy VI mezhdunarodnoj nauchno-prakticheskoj konferentsii i Pervogo mezhregional'nogo simpoziuma rabotnikov ohotnich'ego hozyajstva Rossii. Irkutsk, 2017, pp. 153–159. (In Russ.)

18. Vinober A.V. Ohotovedenie i ohotnich'e hozyajstvo: v poiskah identichnosti, sinhronizatsii i proliferatsii idej (k 70-letiyu fakul'teta ohotovedeniya (1950–2020). Gumanitarnye aspekty okhoty i okhotnich’ego khozyajstva, 2019, no. 6(18), pp. 5–17. (In Russ.)

19. Vodno-bolotnye ugod'ya Rossii. URL: https://www.fesk.ru/tom/3.html (accessed February 20, 2024). (In Russ.

20. Whiteside T.G., Boggs G.S., Maier S.W. Comparing object-based and pixel-based classifications for mapping savannas. International Journal of Applied Earth Observation and Geoinformation, 2011, vol. 13, iss. 6, pp. 884–893.

21. Yang He, Ma Ben, Du Qian. Decision fusion for supervised and unsupervised hyperspectral image classification. International Geoscience and Remote Sensing Symposium (IGARSS), 2009, pp. IV-948–IV-951. DOI: 10.1109/IGARSS.2009.5417535.

22. Zhekulin V.S. Ozero Il'men'. Leningrad: Lenizdat, 1979. 54 p. (In Russ.).