Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 23, 2026
Number 1
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. 1, pp. 63-75

Convolutional neural networks in problems of identification of thermokarst formations based on remote sensing data

V.V. Zhebsain 1 , A.Yu. Gololobov 2 , A.F. Poselsky 1 , N.I. Basharin 3 
1 M.K. Ammosov North-Eastern Federal University, Yakutsk, Russia
2 Yu.G. Shafer Institute of Cosmophysical Research and Aeronomy SB RAS, Yakutsk, Russia
3 Melnikov Permafrost Institute SB RAS, Yakutsk, Russia
Accepted: 01.12.2025
DOI: 10.21046/2070-7401-2026-23-1-63-75
The paper presents the results of numerical experiments to solve the problems of identifying thermokarst polygonal formations that are at an early stage of development and threaten the infrastructure of settlements in the northern regions of Russia, in particular Central Yakutia, using a computer program developed on the basis of neural network technology. The issues of forming two sets of data for conducting numerical experiments, consisting of 3204 and 10 044 verified remote sensing images, respectively, are considered. A database registry for experimental datasets and a web application for its rapid interactive generation have been developed. A series of numerical experiments were conducted to identify images of thermokarst landforms based on training of multilayer convolutional neural networks and direct propagation networks. It is found that convolutional neural networks are more efficient at recognizing thermokarst formations compared to direct propagation networks. The results of a study of the effectiveness of various convolutional neural network models in solving problems of identifying four classes of landscape inhomogeneities, such as thermokarst formations, fields, forests, and reservoirs, are presented. As the results of numerical experiments show, convolutional neural networks make it possible to recognize polygonal thermokarst formations typical of the landscapes of Central Yakutia with a high level of efficiency from graphical remote sensing data. Two models of convolutional neural networks are selected that ensure the best results in the identification of thermokarst formations with average accuracy of about 96 %.
Keywords: thermokarst processes, neural networks, neural network models, image identification, datasets
Full text

References:

  1. Bagaev I. I., Concept analysis neural network and conventional neural network, conventional neural network training using the TensorFlow module, Software of systems in the industrial and social fields, 2020, V. 8, No. 1, pp. 15–22 (in Russian), DOI: 10.18503/2306-2053-2020-8-1-15-22.
  2. Basharin N. I., Egorova L. S., Vasiliev N. F. et al., Using unmanned aerial vehicles for thermokarst activity assessment, Vestnik of North-Eastern Federal University Series “Earth Sciences”, 2020, No. 3(19), pp. 36–44 (in Russian), DOI: 10.25587/SVFU.2020.19.3.005.
  3. Gogoleva P. A., Struchklova S. G., Fedorova E. D., Physico-geographical conditions of the alas landscape development and regularities of the vegetation distribution, Advances in current natural sciences, 2016, No. 12(2), pp. 368–374 (in Russian).
  4. Zhebsain V. V., Poselsky A. F., Identification of thermokarst objects from satellite graphical data using a neural network, Proc. Institute for System Programming of RAS, 2024, V. 36, Iss. 4, pp. 183–190 (in Russian), DOI: 10.15514/ISPRAS-2024-36(4)-14.
  5. Zhebsain V. V., Gololobov A. Yu., Basharing N. I., Poselsky A. F., Features of the use of neural network technology for recognizing of thermokarst objects, Geoinformatika, 2024, No. 4, pp. 39–47 (in Russian), DOI: 10.47148/1609-364X-2024-4-39-47.
  6. Konstantinov P. Ya., Tregubov O. D., Zhang M., Li G., Permafrost temperature dynamics over the last 30 years in certain regions of the eastern sector of the Russian Arctic, Intern. J. Applied Sciences and Technology Integral, 2022, No. 1, pp. 260–267 (in Russian), DOI: 10.55186/02357801_2022_7_1_11.
  7. Fedorov A. N., Konstantinov P. Y., Observations of surface dynamics with thermokarst initiation, Proc. 8th Intern. Conf. on Permafrost, 2003, pp. 239–243.
  8. Fedorov A. N., Konstantinov P. Y., Recent changes in ground temperature and the effect on permafrost landscapes in Central Yakutia, Proc. 9 th Intern. Conf. on Permafrost, 2008, pp. 433–438.
  9. Huang L., Liu L., Luo J. et al., Automatically quantifying evolution of retrogressive thaw slumps in Beiluhe (Tibetan Plateau) from multi-temporal CubeSat images, Intern. J. Applied Earth Observation and Geoinformation, 2021, V. 102, Article 102399, DOI: 10.1016/j.jag.2021.102399.
  10. Hughes-Allen L., Bouchard F., Séjourné A. et al., Automated identification of thermokarst lakes using machine learning in the ice-rich permafrost landscape of Central Yakutia (Eastern Siberia), Remote Sensing, 2023, V. 15, Iss. 5, Article 1226, DOI: 10.3390/rs15051226.
  11. Konstantinov P., Zhelezniak M., Basharin N. et al., Establishing of permafrost thermal monitoring sites in East Siberia, Land, 2020, V. 9, Iss. 12, Article 476, 10 p., DOI: 10.3390/land9120476.
  12. Konstantinov P., Basharin N., Fedorov A. et al., Impact of climate change on the ground thermal regime in the lower Lena region, Arctic Central Siberia, Land, 2023, V. 12, Iss. 1, Article 19, 13 p., DOI: 10.3390/land12010019.
  13. Nitze I., Heidler K., Barth S., Grosse G., Developing and testing a deep learning approach for mapping retrogressive thaw slumps, Remote Sensing, 2021, V. 13, Iss. 21, Article 4294, DOI: 10.3390/rs13214294.
  14. Runge A., Nitze I., Grosse G., Remote sensing annual dynamics of rapid permafrost thaw disturbances with LandTrendr, Remote Sensing of Environment, 2022, V. 268, Article 112752, DOI: 10.1016/j.rse.2021.112752.
  15. Witharana C., Udawalpola M. R., Liljedahl A. K. et al., Automated detection of retrogressive thaw slumps in the high Arctic using high-resolution satellite imagery, Remote Sensing, 2022, V. 14, Iss. 17, Article 4132, DOI: 10.3390/rs14174132.
  16. Yin G., Luo J., Niu F. et al., Machine learning-based thermokarst landslide susceptibility modeling across the permafrost region on the Qinghai-Tibet Plateau, Landslides, 2021, V. 18, pp. 2639–2549, DOI: 10.1007/s10346-021-01669-7.