Buy (120 RUB)
Generate QR code
Open Access
Subscription or Fee Access
The use of neural networks and artificial intelligence in monitoring the thawing of permafrost rocks
https://doi.org/10.15518/isjaee.2025.05.193-209
Abstract
The concept of sustainable development (SD), first presented in the UN report «Our Common Future» (1987), remains a key guideline of modern society, balancing economic progress and environmental stability. This problem is becoming particularly relevant in the context of global climate change, which is most pronounced in the Arctic region, where warming is twice as intense as the global average.
The degradation of permafrost, which occupies about 70% of Russia’s territory, causes serious consequences: thermokarst processes, subsidence of soil and destruction of infrastructure. A striking example was the complete disintegration of the island of Mesyatsev (Franz Josef Land archipelago) in 2024.
Artificial intelligence plays a special role, allowing you to analyze huge arrays of geodata. Neural network models (U-Net, DeepLab, Segment Anything) effectively detect thermokarst lakes, cracks, and other signs of permafrost degradation. However, the application of AI faces methodological challenges: the «big data paradox», the problem of formalizing natural processes, and the skepticism of the scientific community.
The prospects for development are related to the integration of interdisciplinary approaches, the improvement of educational programs and international cooperation between the Arctic states.
About the Author
A. V. Antonov
Federal State Autonomous Educational Institution of Higher Education «Russian University of Transport», RUT (MIIT)
Russian Federation
Russian Federation
Antonov Artem Vladimirovich, postgraduate student, department of «Chemistry and Engineering Ecology»
127994, Moscow, Obraztsova str., 9, p. 9
References
1. Lukmanova R. R. Terminological System «Sustainable Development and Climate Change»: Specifics of the English-Russian Translation of Its Units / R. R. Lukmanova // World of Science, Culture, and Education. – 2025. – No. 1. – Pp. 461-463.
2. Alekseev G. V. The second assessment report of Roshydromet on climate change and their consequences on the territory of the Russian Federation / G. V. Alekseev et al. // Roshydromet. – 2014. – Pp. 1007-1010.
3. Fedorova N. V. The problem of construction and operation of facilities in the conditions of the Far North / N. V. Fedorova, M. I. Ismagilov // Science, education and culture. – 2025. – Pp. 105-108.
4. Rubinstein K. G. The first assessments of the quality of early warning systems for meteorological threats in the Murmansk region / K. G. Rubinstein et al. // Arctic: Ecology and Economy. – 2014. – No. 4 (16). – Pp. 77-85.
5. Kagramanov A. K. Legal Foundations of the Use of Arctic Energy Resources / A. K. Kagramanov // Vector of Legal Science. – 2025. – No. 1. – Pp. 92-101.
6. Porfiryev B. N. Assessment of the Impact of Climate Change on the Russian Economy Using Integrated Assessment Models (IAM) / B. N. Porfiryev, A. Yu. Kolpakov, and E. A. Lazeyeva // Problems of Forecasting. – 2025. – No. 1. – Pp. 49-61.
7. Nikitina E. N. Climate change in the Arctic: adaptation in response to new challenges / E. N. Nikitina // Contours of global transformations: politics, economics, law. – 2019. – No. 5. – Pp. 177-200.
8. Voronkov L. S. Climatic aspects of the EU energy strategy / L. S. Voronkov // Scientific and Analytical Bulletin of IE RAS. – 2024. – No. 1. – Pp. 64-78.
9. Bliznetskaya, E. A. Cities’ Strategies for Adapting to Climate Change in the Context of Multilateral International Cooperation / E. A. Bliznetskaya, A. E. Kuteynikov, and V. I. Shapovalov // Sociology of Science and Technology. – 2024. – No. 1. – Pp.181-199.
10. Osminina T. S. Approaches to the design of engineering and transport systems in the Arctic regions / T. S. Osminina // Architecture and Modern Information Technologies. – 2025. – №1 (70). – Pp. 262-275.
11. Presnov O. M. The construction of piles in permafrost conditions / O. M. Presnov et al. // International Scientific Research Journal. – 2022. – № 2 (116). – Part 1. – Pp. 41-43.
12. Solovyanov, A. A. Multidimensional Arctic / A. A. Solovyanov // Energeticheskaya politika. – 2018. – No. 11. – Pp. 18-22.
13. Ugryumov Yu. V. Organization of the subsystem of state background monitoring of the state of permafrost in the Russian Federation / Yu. V. Ugryumov et al. // Relief and quaternary formations of the Arctic, Subarctic and North-West of Russia. – 2024. – No. 11. – Pp. 602-605.
14. Abramov D. A. Geotemperature Monitoring of the Permafrost Zone in the Magadan Region in 2021-2024 / D. A. Abramov et al. // Relief and Quaternary Formations of the Arctic, Subarctic, and North-West of Russia. – 2024. – No. 11. – Pp. 450-456.
15. Khabarova I. A. Methodology for Remote Sensing / I. A. Khabarova et al. // International Journal of Applied Sciences and Technologies “Integral”. – 2019. – No. 1. – Pp. 21-30.
16. Wenwen Li. GeoAI for Large-Scale Image Analysis and Machine Vision: Recent Progress of Artificial Intelligence in Geography / Li Wenwen, Chia-Yu Hsu // School of Geographical Science and Urban Planning, Arizona State University. – 2022. – № 11(7). – P. 385.
17. Wenwel Li. GeoAI: Where Machine Learning and Big Data Converge in GIScience / Li Wenwen / Journal of Spatial Information Science. – 2020. – № 20. – Pp. 71-77.
18. Goodchild M. F. Replication across Space and Time Must Be Weak in the Social and Environmental Sciences / M. F. Goodchild, Li Wenwen / Proceedings of the National Academy of Sciences. – 2021. – № 35. – P. 118.
19. Jordan Beer/ Uncrewed Aerial Vehicle–Based Assessments of Peatland Permafrost Vulnerability Along the Labrador Sea Coastline, Northern Canada / Jordan Beer and others // Permafrost and Periglacial Processes. – 2024. – № 35. – Pp. 461-477.
20. Final report on the activities of Roshydromet in 2023 and tasks for 2024. Ministry of Natural Resources and Environment of the Russian Federation. Federal Service for Hydrometeorology and Environmental Monitoring (Roshydromet). – 2024. – Pp. 44-47.
21. Sofia Antonova. Spatio-temporal variability of X-band radar backscatter and coherence over the Lena River Delta, Siberia / Antonova Sofia and others // Remote Sensing of Environment. – 2016. – № 182. – Pp. 169-191.
22. Annett Bartsch. Permafrost Monitoring from Space / Annett Bartsch, Tazio Strozzi, Ingmar Nitze // Surveys in Geophysics. – 2023. – № 5. – Pp. 1579-1614.
23. Chih-Li Chang. Main-chain engineering of polymer photocatalysts with hydrophilic non-conjugated segments for visible-light-driven hydrogen evolution / Chih-Li Chang and others // Nature Communications. – 2022. – № 13. – Pp. 1-11.
24. Arctic Council Secretariat Annual Report 2023 / Arctic Council Secretariat. – 2024. – Pp. 180-181.
25. Xiaochen Zou. Potential of Satellite Spectral Resolution Vegetation Indices for Estimation of Canopy Chlorophyll Content of Field Crops: Mitigating Effects of Leaf Angle Distribution / Xiaochen Zou, Jun Jin, Matti Mõttus // Remote Sensing. – 2023. – № 15. – Pp. 1-22.
26. Stefano Ponti. Thermal photogrammetry on a permafrost rock wall for the active layer monitoring / Stefano Ponti, Irene Girola, Mauro Guglielmin // Science of the Total Environment. – 2024. – № 914. – Pp. 1-15
27. Goncharov A. M. Artificial Intelligence as the Main Direction of Development of Robotic Systems / A. M. Goncharov, S. V. Ryabov // Military Thought. – 2021. – No. 6. – Pp. 65-70.
28. Krinitsky M. A. AI and the Ocean: Report on Mikhail Krinitsky’s Presentation at the AI IN2023 Conference / M. A. Krinitsky // Environment and Energy Science. – 2023. – No. 3. – Pp. 33-38.
29. Lukashik D. V. Analysis of Modern Methods of Image Segmentation / D. V. Lukashik // Economy and Quality of Communication Systems. – 2022. – No. 2. – Pp. 57-64.
30. Dorrer G. A. Semantic Segmentation of Images Using Convolutional Neural Networks / G. A. Dorrer, M. S. Koryukin // Section «Information and Control Systems». – 2017. – Vol. 2. – Pp. 141-143.
31. Kazantseva L. V. Image segmentation in unmanned image algorithms / L. V. Kazantseva, I. I. Yurov // Colloquium-journal. – 2020. – № 2 (54). – Pp. 24-26.
32. Belova Yu. V. Development of an algorithm for semantic segmentation of remote sensing data for determining phytoplankton populations / Yu. V. Belov, I. F. Razveeva, E. O. Rakhimbayeva // Advanced Engineering Research (Rostov-on-Don). – 2024. – № 24 (3). – Pp. 283-292.
33. Baborykin M. Y. Decoding of aerospace survey materials for the analysis of engineering and geological conditions in the general algorithm of surveys on linear objects. Baborykin // Engineering Research. – 2014. – No. 9-10. – Pp. 13-21.
34. Li Y. Mvitv2: Improved multiscale vision transformers for classification and detection. In Proceedings of the IEEE / CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18-24 June 2022; pp. 4804-4814.
35. Druki A. A. Semantic segmentation of Earth remote sensing data using neural network algorithms / A. A. Druki et al. // Izvestiya Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov. – 2018. – No. 329 (1). – Pp. 59-68.
36. Yusupov B. N. On Earth remote sensing data / B. N. Yusupov, Sh. Sh. Ochilov // Economy and society. – 2023. – No. 12(115)-1. – Pp. 1618-1625.
37. Dolgopolov D. V. Analysis of the accuracy of the initial data used in modeling the relief and profile of the route of main pipelines / D. V. Dolgopolov et al. // Izvestiya of Tomsk Polytechnic University. Engineering of Georesources. – 2022. – Vol. 333. – No. 4. – Pp. 168-180.
38. Georgi M. Yu. Methods of Extracting Causality from Observational Data in the Practice of Artificial Intelligence / M. Yu. Georgi // Izvestiya of the Southern Federal University. Technical Sciences. – 2023. – No. 1. – Pp. 125-134.
39. Alexander Kirillov. Segment Anything / Kirillov A. and others // Computer Vision and Pattern Recognition. – 2023. – № 6. – Pp. 1148-1152.
40. Justine Ramage. The Net GHG Balance and Budget of the Permafrost Region (2000-2020) From Ecosystem Flux Upscaling / Justine Ramage and others // Global Biogeochemical Cycles. – 2024. – Pp. 1-18.
41. Wenwen Li. Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model’s Generalizability in Permafrost Mapping / Wenwen Li and others // Remote sensing. – 2024. – № 16. – P. 797.
42. Ya-Lun. Monitoring Arctic permafrost coastal erosion dynamics using a multidecadal cross-mission SAR dataset along an Alaskan Beaufort Sea coastline / Ya-Lun, S. Tsai // Science of the Total Environment. – 2024. – № 917. – Pp. 329-33.
43. Sustainable Development Report of the Norilsk Nickel Group of Companies for 2024. Contribution to the Well-Being of Generations. – 2025. – P. 143.
44. Serik Nurakynov. Application of Artificial Intelligence in Glacier Studies: A State-of-the-Art Review / Serik Nurakynov and others // Multidisciplinary Digital Publishing Institute. – 2024. – № 16, 2272.
45. Shengnan Zhang. Plant nitrogen acquisition from inorganic and organic sources via root and mycelia pathways in ectomycorrhizal alpine forests / Shengnan Zhang, and others // Soil Biology and Biochemistry. – 2019. – № 136. – P. 107517
46. Wang S. Opportunities and Threats of Cryosphere Change to the Achievement of UN 2030 SDGs / S. Wang and others // Humanit. Soc. Sci. Commun. – 2024 – № 11. – P. 44.
47. Peng Y. Automated Glacier Extraction Using a Transformer Based Deep Learning Approach from Multi-Sensor Remote Sensing Imagery / Y. Peng and others // ISPRS J. Photogramm. Remote Sens. – 2023. – № 202. – Pp. 303-313.
48. Han W. A Survey of Machine Learning and Deep Learning in Remote Sensing of Geological Environment: Challenges, Advances, and Opportunities / W. Han and others // ISPRS J. Photogramm. Remote Sens. – 2023. – № 202. – Pp. 87-113.
49. Zhang H. K. Machine Learning and Deep Learning in Remote Sensing Data Analysis. Reference Module in Earth Systems and Environmental Sciences / H. K. Zhang // Elsevier: Amsterdam. – 2024. – № 10. – Pp. 147-155.
50. Michael Chui. The economic potential of generative AI / Michael Chui and others // McKinsey & Company. – 2023. – P. 57.
51. Jones B. M. A decade of thermokarst dynamics and landscape evolution revealed by time-lapse photography in Arctic Alaska. / B. M. Jones, L. M. Farquharson, C. A. Baughman // Environmental Research Letters. – 2020. – № 15(12). – Pp. 145-156.
52. Elias Manos. Permafrost thaw-related infrastructure damage costs in Alaska are projected to double under medium and high emission scenarios / Elias Manos, Chandi Witharana, Anna K. Liljedahl // Communications earth & environment. – 2025. – № 6. – Pp. 1-11.
Review
For citations:
Antonov A.V. The use of neural networks and artificial intelligence in monitoring the thawing of permafrost rocks. Alternative Energy and Ecology (ISJAEE). 2025;(5):193-209. (In Russ.) https://doi.org/10.15518/isjaee.2025.05.193-209
Views:
14
Email this article 