Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine Learning

Freezing and thawing (FT) processes in the soil active layer play a critical role in high-latitude ecosystems, influencing carbon cycling, hydrology, and infrastructure stability. Accurate prediction of FT states is essential for assessing permafrost dynamics under a changing climate. This study int...

Full description

Saved in:
Bibliographic Details
Main Authors: A. Ahajjam, M. Soaper, R. Chance, J. Chandler, T. Pasch
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:International Journal of Applied Earth Observations and Geoinformation
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1569843225002237
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850123774680104960
author A. Ahajjam
M. Soaper
R. Chance
J. Chandler
T. Pasch
author_facet A. Ahajjam
M. Soaper
R. Chance
J. Chandler
T. Pasch
author_sort A. Ahajjam
collection DOAJ
description Freezing and thawing (FT) processes in the soil active layer play a critical role in high-latitude ecosystems, influencing carbon cycling, hydrology, and infrastructure stability. Accurate prediction of FT states is essential for assessing permafrost dynamics under a changing climate. This study introduces a comprehensive framework for FT state prediction that leverages MERRA-2 reanalysis climate data, ensemble machine learning, and in-situ soil temperature measurements. In addition, Genetic algorithms are employed to identify the most influential geospatial features affecting FT transitions across three shallow active layer depths. The framework is validated in two distinct regions on Alaska’s North Slope (Deadhorse and Toolik Lake) over four prediction horizons (+0, +7, +30, and +90 days). Furthermore, the study evaluates the impact of four training approaches (location-specific, cross-location, location-agnostic, and depth-agnostic) on model performance, addressing the challenge of using prediction methods in real-world scenarios.
format Article
id doaj-art-8f41b9a0f7ca4bad9d979485951c452d
institution OA Journals
issn 1569-8432
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series International Journal of Applied Earth Observations and Geoinformation
spelling doaj-art-8f41b9a0f7ca4bad9d979485951c452d2025-08-20T02:34:31ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-06-0114010457610.1016/j.jag.2025.104576Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine LearningA. Ahajjam0M. Soaper1R. Chance2J. Chandler3T. Pasch4School of Electrical Engineering and Computer Science, University of North Dakota, Upson Hall I, Grand Forks, 58202-7165, ND, USA; Corresponding author.Harold Hamm School of Geology and Geologic Engineering, University of North Dakota, Leonard Hall, Grand Forks, 58202-8358, ND, USAHarold Hamm School of Geology and Geologic Engineering, University of North Dakota, Leonard Hall, Grand Forks, 58202-8358, ND, USADepartment of Communication, University of North Dakota, O’Kelly Hall, Grand Forks, 58202, ND, USADepartment of Communication, University of North Dakota, O’Kelly Hall, Grand Forks, 58202, ND, USAFreezing and thawing (FT) processes in the soil active layer play a critical role in high-latitude ecosystems, influencing carbon cycling, hydrology, and infrastructure stability. Accurate prediction of FT states is essential for assessing permafrost dynamics under a changing climate. This study introduces a comprehensive framework for FT state prediction that leverages MERRA-2 reanalysis climate data, ensemble machine learning, and in-situ soil temperature measurements. In addition, Genetic algorithms are employed to identify the most influential geospatial features affecting FT transitions across three shallow active layer depths. The framework is validated in two distinct regions on Alaska’s North Slope (Deadhorse and Toolik Lake) over four prediction horizons (+0, +7, +30, and +90 days). Furthermore, the study evaluates the impact of four training approaches (location-specific, cross-location, location-agnostic, and depth-agnostic) on model performance, addressing the challenge of using prediction methods in real-world scenarios.http://www.sciencedirect.com/science/article/pii/S1569843225002237Freeze-thaw cycleSoil temperatureMERRA-2Machine learningAlaskaArctic
spellingShingle A. Ahajjam
M. Soaper
R. Chance
J. Chandler
T. Pasch
Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine Learning
International Journal of Applied Earth Observations and Geoinformation
Freeze-thaw cycle
Soil temperature
MERRA-2
Machine learning
Alaska
Arctic
title Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine Learning
title_full Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine Learning
title_fullStr Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine Learning
title_full_unstemmed Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine Learning
title_short Predicting Freeze-Thaw States in Alaska Permafrost Landscapes using climate Reanalysis and Machine Learning
title_sort predicting freeze thaw states in alaska permafrost landscapes using climate reanalysis and machine learning
topic Freeze-thaw cycle
Soil temperature
MERRA-2
Machine learning
Alaska
Arctic
url http://www.sciencedirect.com/science/article/pii/S1569843225002237
work_keys_str_mv AT aahajjam predictingfreezethawstatesinalaskapermafrostlandscapesusingclimatereanalysisandmachinelearning
AT msoaper predictingfreezethawstatesinalaskapermafrostlandscapesusingclimatereanalysisandmachinelearning
AT rchance predictingfreezethawstatesinalaskapermafrostlandscapesusingclimatereanalysisandmachinelearning
AT jchandler predictingfreezethawstatesinalaskapermafrostlandscapesusingclimatereanalysisandmachinelearning
AT tpasch predictingfreezethawstatesinalaskapermafrostlandscapesusingclimatereanalysisandmachinelearning