A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment

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 c...

Full description

Saved in:
Bibliographic Details
Main Authors: Polina Pilyugina, Timofey Chernikov, Maria Smirnova, Alexey Zaytsev, Alexander Bulkin, Evgeny Burnaev, Ilya S. Belalov, Nazar Sotiriadi, Albert Efimov, Yury Maximov, Oleg Anisimov
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11014074/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850101145773539328
author Polina Pilyugina
Timofey Chernikov
Maria Smirnova
Alexey Zaytsev
Alexander Bulkin
Evgeny Burnaev
Ilya S. Belalov
Nazar Sotiriadi
Albert Efimov
Yury Maximov
Oleg Anisimov
author_facet Polina Pilyugina
Timofey Chernikov
Maria Smirnova
Alexey Zaytsev
Alexander Bulkin
Evgeny Burnaev
Ilya S. Belalov
Nazar Sotiriadi
Albert Efimov
Yury Maximov
Oleg Anisimov
author_sort Polina Pilyugina
collection DOAJ
description 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.
format Article
id doaj-art-eff013845a904bb0bb8fd75c3c97de05
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-eff013845a904bb0bb8fd75c3c97de052025-08-20T02:40:07ZengIEEEIEEE Access2169-35362025-01-0113964239643310.1109/ACCESS.2025.357307211014074A Physics-Informed Machine Learning Framework for Permafrost Stability AssessmentPolina Pilyugina0https://orcid.org/0009-0009-2838-4759Timofey Chernikov1https://orcid.org/0009-0004-8192-3751Maria Smirnova2https://orcid.org/0009-0001-2005-3367Alexey Zaytsev3https://orcid.org/0000-0002-1653-0204Alexander Bulkin4https://orcid.org/0000-0002-2052-8190Evgeny Burnaev5https://orcid.org/0000-0001-8424-0690Ilya S. Belalov6https://orcid.org/0000-0002-5447-4872Nazar Sotiriadi7https://orcid.org/0009-0006-1116-896XAlbert Efimov8https://orcid.org/0000-0001-6857-8659Yury Maximov9Oleg Anisimov10Skolkovo Institute of Science and Technology, Moscow, RussiaMoscow Institute of Physics and Technology, Moscow, RussiaMoscow Institute of Physics and Technology, Moscow, RussiaSkolkovo Institute of Science and Technology, Moscow, RussiaInternational Center for Corporate Data Analysis, Saint Martin d’Hères, FranceSkolkovo Institute of Science and Technology, Moscow, RussiaFRC Biotechnology RAS, Moscow, RussiaSberbank of Russia PJSC, Moscow, RussiaSber Innovation and Research, Sberbank of Russia, Moscow, RussiaLos Alamos National Laboratory, Los Alamos, NM, USAState Hydrological Institute, St. Petersburg, RussiaGlobal 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.https://ieeexplore.ieee.org/document/11014074/Permafrost thawclimate changephysics-informed machine learning framework
spellingShingle Polina Pilyugina
Timofey Chernikov
Maria Smirnova
Alexey Zaytsev
Alexander Bulkin
Evgeny Burnaev
Ilya S. Belalov
Nazar Sotiriadi
Albert Efimov
Yury Maximov
Oleg Anisimov
A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment
IEEE Access
Permafrost thaw
climate change
physics-informed machine learning framework
title A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment
title_full A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment
title_fullStr A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment
title_full_unstemmed A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment
title_short A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment
title_sort physics informed machine learning framework for permafrost stability assessment
topic Permafrost thaw
climate change
physics-informed machine learning framework
url https://ieeexplore.ieee.org/document/11014074/
work_keys_str_mv AT polinapilyugina aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT timofeychernikov aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT mariasmirnova aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT alexeyzaytsev aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT alexanderbulkin aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT evgenyburnaev aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT ilyasbelalov aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT nazarsotiriadi aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT albertefimov aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT yurymaximov aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT oleganisimov aphysicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT polinapilyugina physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT timofeychernikov physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT mariasmirnova physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT alexeyzaytsev physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT alexanderbulkin physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT evgenyburnaev physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT ilyasbelalov physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT nazarsotiriadi physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT albertefimov physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT yurymaximov physicsinformedmachinelearningframeworkforpermafroststabilityassessment
AT oleganisimov physicsinformedmachinelearningframeworkforpermafroststabilityassessment