A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment

Pilyugina P. Chernikov T. Smirnova M. Zaytsev A. Bulkin A. Burnaev E. Belalov I.S. Sotiriadi N. Efimov A. Maximov Y. Anisimov O.
2025 Institute of Electrical and Electronics Engineers Inc.

IEEE Access
2025 #13 96423 - 96433 pp.

Global warming accelerates permafrost degradation, compromising the reliability of critical infrastructure relied upon by over five million people daily. Additionally, permafrost thaw releases substantial methane emissions due to the thawing of swamps, further amplifying global warming and climate change and thus posing a significant threat to more than eight billion people worldwide. To mitigate this growing risk, policymakers and stakeholders need accurate predictions of permafrost thaw progression. Comprehensive physics-based permafrost models often require complex, location-specific fine-tuning, making them impractical for widespread use. Although simpler models with fewer input parameters offer convenience, they generally lack accuracy. Purely data-driven models also face limitations due to the spatial and temporal sparsity of observational data. This work develops a physics-informed machine learning framework to predict permafrost thaw rates. By integrating a physics-based model into machine learning, the framework significantly enhances the feature set, enabling models to train on higher-quality data. This approach improves permafrost thaw rate predictions, supporting more reliable decision-making for construction and infrastructure maintenance in permafrost-vulnerable regions, with a forecast horizon spanning several decades.

climate change , Permafrost thaw , physics-informed machine learning framework

Text of the article Перейти на текст статьи

Skolkovo Institute of Science and Technology, Moscow, 143026, Russian Federation
Moscow Institute of Physics and Technology, Moscow, 141701, Russian Federation
Sberbank of Russia PJSC, Moscow, 117997, Russian Federation
Beijing Institute of Mathematical Sciences and Applications, Beijing, 101408, China
International Center for Corporate Data Analysis, Saint Martin d’Hères, 38402, France
Moscow State University, Moscow, 119991, Russian Federation
International Center for Corporate Data Analysis, Astana, 631301, Kazakhstan
Artificial Intelligence Research Institute (AIRI), Moscow, 105064, Russian Federation
FRC Biotechnology RAS, Moscow, 117312, Russian Federation
Sberbank of Russia, Sber Innovation and Research, Moscow, 117312, Russian Federation
Los Alamos National Laboratory, Los Alamos, 87545, NM, United States
State Hydrological Institute, St. Petersburg, 199004, Russian Federation

Skolkovo Institute of Science and Technology
Moscow Institute of Physics and Technology
Sberbank of Russia PJSC
Beijing Institute of Mathematical Sciences and Applications
International Center for Corporate Data Analysis
Moscow State University
International Center for Corporate Data Analysis
Artificial Intelligence Research Institute (AIRI)
FRC Biotechnology RAS
Sberbank of Russia
Los Alamos National Laboratory
State Hydrological Institute

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026