Tuning parameters of a sea ice model using machine learning

We developed a new method for tuning sea ice rheology parameters, which consists of two components: a new metric for characterising sea ice deformation patterns and an ML-based approach for tuning rheology parameters. We applied the new method to tune the parametrisation of the brittle Bingham-Maxwe...

Full description

Bibliographic Details
Main Authors: Korosov, Anton, Ying, Yue, Olason, Einar
Format: Text
Language:English
Published: 2024
Subjects:
Online Access:https://doi.org/10.5194/egusphere-2024-2527
https://egusphere.copernicus.org/preprints/2024/egusphere-2024-2527/
id ftcopernicus:oai:publications.copernicus.org:egusphere122510
record_format openpolar
spelling ftcopernicus:oai:publications.copernicus.org:egusphere122510 2024-09-15T18:34:32+00:00 Tuning parameters of a sea ice model using machine learning Korosov, Anton Ying, Yue Olason, Einar 2024-08-27 application/pdf https://doi.org/10.5194/egusphere-2024-2527 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-2527/ eng eng doi:10.5194/egusphere-2024-2527 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-2527/ eISSN: Text 2024 ftcopernicus https://doi.org/10.5194/egusphere-2024-2527 2024-08-28T05:24:22Z We developed a new method for tuning sea ice rheology parameters, which consists of two components: a new metric for characterising sea ice deformation patterns and an ML-based approach for tuning rheology parameters. We applied the new method to tune the parametrisation of the brittle Bingham-Maxwell rheology (BBM) implemented and used in the next-generation sea-ice model (neXtSIM). As a reference dataset, we used sea ice drift and deformation observations from the Radarsat Geophysical Processing System (RGPS). The metric characterises a field of sea ice deformation with a vector of values. It includes well-established descriptors such as the mean and standard deviation of deformation, the structure-function of the spatial scaling analysis, and the density and intersection of linear kinematic features (LKFs). We added more descriptors to the metric that characterise the pattern of ice deformation, including image anisotropy and Haralick texture features. The developed metric can describe ice deformation from any model or satellite platform. In the parameter tuning method, we first run an ensemble of neXtSIM members with perturbed rheology parameters and then train a machine-learning model using the simulated data. We provide the descriptors of ice deformation as input to the ML model and rheology parameters as targets. We apply the trained ML model to the descriptors computed from RGPS observations. The developed ML-based method is generic and can be used to tune the parameters of any model. We ran experiments with tens of members and found optimal values for four neXtSIM BBM parameters: scaling parameter for ridging ( P 0 ≈ 5.1 kPa), cohesion at the reference scale ( c ref ≈ 1.2 MPa), internal friction angle tangent ( µ ≈ 0.7), ice–atmosphere drag coefficient ( C A ≈ 0.00228). A NeXtSIM run with the optimal parametrisation produces maps of sea ice deformation visually indistinguishable from the RGPS observations. These parameters exhibit weak ... Text Sea ice Copernicus Publications: E-Journals
institution Open Polar
collection Copernicus Publications: E-Journals
op_collection_id ftcopernicus
language English
description We developed a new method for tuning sea ice rheology parameters, which consists of two components: a new metric for characterising sea ice deformation patterns and an ML-based approach for tuning rheology parameters. We applied the new method to tune the parametrisation of the brittle Bingham-Maxwell rheology (BBM) implemented and used in the next-generation sea-ice model (neXtSIM). As a reference dataset, we used sea ice drift and deformation observations from the Radarsat Geophysical Processing System (RGPS). The metric characterises a field of sea ice deformation with a vector of values. It includes well-established descriptors such as the mean and standard deviation of deformation, the structure-function of the spatial scaling analysis, and the density and intersection of linear kinematic features (LKFs). We added more descriptors to the metric that characterise the pattern of ice deformation, including image anisotropy and Haralick texture features. The developed metric can describe ice deformation from any model or satellite platform. In the parameter tuning method, we first run an ensemble of neXtSIM members with perturbed rheology parameters and then train a machine-learning model using the simulated data. We provide the descriptors of ice deformation as input to the ML model and rheology parameters as targets. We apply the trained ML model to the descriptors computed from RGPS observations. The developed ML-based method is generic and can be used to tune the parameters of any model. We ran experiments with tens of members and found optimal values for four neXtSIM BBM parameters: scaling parameter for ridging ( P 0 ≈ 5.1 kPa), cohesion at the reference scale ( c ref ≈ 1.2 MPa), internal friction angle tangent ( µ ≈ 0.7), ice–atmosphere drag coefficient ( C A ≈ 0.00228). A NeXtSIM run with the optimal parametrisation produces maps of sea ice deformation visually indistinguishable from the RGPS observations. These parameters exhibit weak ...
format Text
author Korosov, Anton
Ying, Yue
Olason, Einar
spellingShingle Korosov, Anton
Ying, Yue
Olason, Einar
Tuning parameters of a sea ice model using machine learning
author_facet Korosov, Anton
Ying, Yue
Olason, Einar
author_sort Korosov, Anton
title Tuning parameters of a sea ice model using machine learning
title_short Tuning parameters of a sea ice model using machine learning
title_full Tuning parameters of a sea ice model using machine learning
title_fullStr Tuning parameters of a sea ice model using machine learning
title_full_unstemmed Tuning parameters of a sea ice model using machine learning
title_sort tuning parameters of a sea ice model using machine learning
publishDate 2024
url https://doi.org/10.5194/egusphere-2024-2527
https://egusphere.copernicus.org/preprints/2024/egusphere-2024-2527/
genre Sea ice
genre_facet Sea ice
op_source eISSN:
op_relation doi:10.5194/egusphere-2024-2527
https://egusphere.copernicus.org/preprints/2024/egusphere-2024-2527/
op_doi https://doi.org/10.5194/egusphere-2024-2527
_version_ 1810476426444406784