Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 23, 2026
Number 1 Number 2
Volume 22, 2025
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2026, V. 23, No. 2, pp. 173-187

Assessing the quality of forest vegetation condition identification using Shchuchye Ozero Nature Reserve as an example

V.A. Zelentsov 1 , V.F. Mochalov 1 
1 Saint Petersburg Federal Research Center RAS, Saint Petersburg, Russia
Accepted: 18.12.2025
DOI: 10.21046/2070-7401-2026-23-2-173-187
The article examines aspects of joint and simultaneous processing of multispectral satellite imagery and assessment of processing results quality for the task of forest vegetation condition identification. The role of a well-founded composition of initial data on forest vegetation classification for these purposes is emphasized. A methodology is presented that includes preliminary and final assessments of imagery processing quality. The key element of the method is a new approach to determining at a preliminary stage a set of elementary sites (pixels) of the analyzed scene fragment for their use as initial data when processing satellite images. The selection of elementary sites is based on the use of fuzzy clustering and quantitative analysis of the degree of each pixel membership in one of the classes of forest landscape identifiable elements. The degree of membership is used to determine the composition of elementary sites that require clarification, including through field surveys. Final data processing and processing quality assessment for the entire analyzed scene are performed using refined initial data. The analysis of processing quality using the proposed methodology is demonstrated by the example of classifying spruce forest condition in fire hazard classes in Lake Shchuchye Nature Reserve in Leningrad Region. Sentinel 2 multispectral data were used in this case, and algorithms for calculating various vegetation indices were applied. To justify the selection of the initial data, preliminary fuzzy clustering of a 400-pixel scene fragment was performed. Thirty-nine pixels requiring clarification were identified, and the entire scene was processed using these clarified values. It is shown that the application of this methodology improves the final processing quality indicators, significantly reduces the time spent on preparing the initial data, and also helps formulate recommendations for selecting processing algorithms that ensure the best identification quality. In the considered example, these are the algorithms for calculating the Normalized Difference Vegetation Index (NDVI) and the Atmospherically Resistant Vegetation Index (ARVI). The most effective area of application of the methodology is solving multispectral data processing problems for relatively small areas of territory, since it allows for the most complete consideration of local features and specific spectral-reflective characteristics of landscape elements.
Keywords: multispectral satellite imagery, processing quality indicators, initial data, processing algorithms, forest vegetation condition identification, fuzzy clustering, field surveys, fire hazard classes
Full text

References:

  1. Gorelik A. L., Skripkin V. A., Metody raspoznavaniya: uchebnoe posobie dlya vuzov (Recognition methods: A textbook for universities), 4th ed., corr. Moscow: Vysshaya shkola, 2004, 261 p. (in Russian).
  2. Demidova L. A., Konjaeva E. I., Clustering of objects using the FCM algorithm based on fuzzy sets of the second type and the genetic algorithm, Vestnik of Ryazan State Radio Engineering University, 2008, No. 4, Iss. 26, 9 p. (in Russian).
  3. Zelentsov V. A., Mochalov V. F. (2024a), An example of evaluating the quality of the results of automated identification of forest vegetation, 9-ya Vserossiiskaya nauchno-tehnicheskaya konferentsiya “Lesa Rossii: politika, promyshlennost’, nauka, obrazovanie”: materialy konferentsii (Proc. 9th All-Russian Scientific and Technical Conf. “Forests of Russia: Politics, Industry, Science, Education”), Saint Petersburg: SPbGLTU, 2024, pp. 46–49 (in Russian).
  4. Zelentsov V. A., Mochalov V. F. (2024b), Indicators and algorithms for assessing the quality of the results of identification of the condition of adjacent territories, Intellektual’nye tehnologii na transporte, 2024, No. 3(39), pp. 73–82 (in Russian), DOI: 10.20295/2413-2527-2024-339-73-82.
  5. Zelentsov V. A., Mochalov V F., Mukhametov D. I., Methodology of ground surveys of forest vegetation for the organization of automated processing of multispectral satellite survey materials, 10-ya Vserossiiskaya nauchno-tehnicheskaya konferentsiya “Lesa Rossii: politika, promyshlennost’, nauka, obrazovanie”: materialy konferentsii (Proc. 10th All-Russian Scientific and Technical Conf. “Forests of Russia: Politics, Industry, Science, Education”), Saint Petersburg: SPbGLTU, 2025, pp. 78–80 (in Russian).
  6. Ivanov V. S., Osnovy matematicheskoi statistiki: uchebnoe posobie dlya vuzov (Fundamentals of mathematical statistics: A textbook for universities), Moscow: Fizkul’tura i sport, 1990, 176 p. (in Russian).
  7. Kiselev A. V., Tronin A. A., Kritsuk S. G. et al., Long-term dynamics of spruce forests of Lake Shchuchye Reserve based on satellite data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2025, V. 22, No. 2, pp. 173–185 (in Russian), DOI: 10.21046/2070-7401-2025-22-2-173-185.
  8. Komarov A. A., Kirsanov A. D., Malashin S. N., Comparative characteristics of various vegetation indices (VI) when the vegetation cover state of forage grasses assessing, Izvestiya of Saint-Petersburg State Agrarian University, 2021, No. 2(63), pp. 18–29 (in Russian), DOI: 10.24412/2078-1318-2021-2-18-29.
  9. Malyshev B. V., Fomin B. N., Decentralized database of spectral characteristics and parameters of Earth surface features, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, V. 16, No. 2, pp. 53–65 (in Russian), DOI: 10.21046/2070-7401-2019-16-2-53-65.
  10. Mochalov V. F., Grigor’eva O. V., Spesivtseva K. A., Assessment of forest characteristics based on national space survey data, 8-ya Vserossiiskaya nauchno-tehnicheskaya konferentsiya “Lesa Rossii: politika, promyshlennost’, nauka, obrazovanie”: materialy konferentsii (Proc. 8th All-Russian Scientific and Technical Conference “Forests of Russia: Politics, Industry, Science, Education”), Saint Petersburg: SPbGLTU, 2023, pp. 79–82 (in Russian).
  11. Mylnikova T. A., Borovlev A. Yu., Elsakov V. V., Shchanov V. M., Formation of a spatial database of tree species distribution at Lyalsky test site (Komi Republic) based on UAV data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2025, V. 22, No. 1, pp. 116–130 (in Russian), DOI: 10.21046/2070-7401-2025-22-1-116-130.
  12. Prikaz Rosleskhoza “Ob utverzhdenii klassifikatsii prirodnoi pozharnoi opasnosti lesov i klassifikatsii pozharnoi opasnosti v lesakh v zavisimosti ot uslovii pogody” (Order of the Federal Forestry Agency “On approval of the classification of natural fire danger of forests and classification of fire danger in forests depending on weather conditions”), 05.07.2011, No. 287 (in Russian).
  13. Raschka S., Python Machine Learning, 1st ed. Packt Publishing, 2015, 454 p.
  14. Savorskiy V. P., Kashnickiy A. V., Konstantinova A. M. et al., Capabilities of hyperspectral indices analysis of the Vega-Constellation remote monitoring information systems, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2016, V. 13, No. 3, pp. 28–45 (in Russian), DOI: 10.21046/2070-7401-2016-13-3-28-45.
  15. Hastie T., Tibshirani R., Friedman J., The elements of statistical learning. Data mining, inference, and prediction, 2nd ed., New York: Springer, 2009, 767 p.
  16. Bezdek J. C., Pattern recognition with fuzzy objective function algorithms, New York: Springer, 1981, 272 p., DOI: 10.1007/978-1-4757-0450-1.
  17. Bradley A. P., The use of the area under the ROC curve in the evaluation of machine learning algorithms, Pattern Recognition, 1997, V. 30, Iss. 7, pp. 1145–1159, DOI: 10.1016/S0031-3203(96)00142-2.
  18. Brovkina O., Cienciala E., Zemek F. et al., Composite indicator for monitoring of Norway spruce stand decline, European J. Remote Sensing, 2017, V. 50, Iss. 1, pp. 550–563, DOI: 10.1080/22797254.2017.1372697.
  19. Congalton R. G., Green K., Assesing the accuracy of remotely sensed data. Principles and practices, 2nd ed., CRC Press, 2009, 209 p.
  20. Ferreira M. P., Wagner F. H., Aragão L. E. et al., Tree species classification in tropical forests using visible to shortwave infrared WorldView-3 images and texture analysis, ISPRS J. Photogrammetry and Remote Sensing, 2019, V. 149, pp. 119–131, DOI: 10.1016/j.isprsjprs.2019.01.019.
  21. Hollander M., Wolfe D., Nonparametric statistical methods, 2nd ed., New York: Wiley, 1999, 787 p.
  22. Liu Y., Ren C., Liang J. et al., A robust index based on phenological features to extract sugarcane from multisource remote sensing data, Remote Sensing, 2023, V. 15, Iss. 24, Article 5783, DOI: 10.3390/ rs15245783.
  23. Liu P., Ren C., Wang Z. et al., Evaluating the potential of Sentinel 2 time series imagery and machine learning for tree species classification in a mountainous forest, Remote Sensing, 2024, V. 16, Iss. 2, Article 293, DOI: 10.3390/rs16020293.
  24. Maxwell A. E., Warner T. A., Guillén L. A. (2021a), Accuracy assessment in convolutional neural network-based deep learning remote sensing studies — Part 1: Literature review, Remote Sensing, 2021, V. 13, Iss. 13, Article 2450, DOI: 10.3390/rs13132450.
  25. Maxwell A. E., Warner T. A., Guillén L. A. (2021b), Accuracy assessment in convolutional neural network-based deep learning remote sensing studies — Part 2: Recommendations and best practices, Remote Sensing, 2021, V. 13, Iss. 13, Article 2591, DOI: 10.3390/rs13132591.
  26. Mochalov V., Grigorieva O., Zhukov D. et al., Remote sensing image processing based on modified fuzzy algorithm, In: Artificial Intelligence and Bioinspired Computational Methods: Proc. 9th Computer Science On-line Conf. 2020, Ser.: Advances in Intelligent Systems and Computing, 2020, V. 1225, pp. 563–572, DOI: 10.1007/978-3-030-51971-1_46.
  27. Schowengerdt R., Remote Sensing, models and methods for image processing, London: Academic Press, 2007, 560 p.
  28. Wang B., Yao Y., Mountain vegetation classification method based on multi-channel semantic segmentation model, Remote Sensing, 2024, V. 16, Iss. 2, Article 256, DOI: 10.3390/rs16020256.
  29. Zhao B., Mi Y., Sun R., Wu C., Semantic segmentation method of residential areas in remote sensing images based on cross-attention mechanism, Remote Sensing, 2025, V. 17, Iss. 18, Article 3253, DOI: 10.3390/rs17183253.