Deep learning speeds up ice flow modelling by several orders of magnitude
This paper introduces the Instructed Glacier Model (IGM) – a model that simulates ice dynamics, mass balance and its coupling to predict the evolution of glaciers, icefields or ice sheets. The nov elty of IGM is that it models the ice flow by a Convolutional Neural Network, which is trained from dat...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Cambridge University Press
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/20.500.11850/523822 https://doi.org/10.3929/ethz-b-000523822 |
id |
ftethz:oai:www.research-collection.ethz.ch:20.500.11850/523822 |
---|---|
record_format |
openpolar |
spelling |
ftethz:oai:www.research-collection.ethz.ch:20.500.11850/523822 2023-05-15T16:57:31+02:00 Deep learning speeds up ice flow modelling by several orders of magnitude Jouvet, Guillaume Cordonnier, Guillaume Kim, Byungsoo Lüthi, Martin Vieli, Andreas Aschwanden, Andy 2022-08 application/application/pdf https://hdl.handle.net/20.500.11850/523822 https://doi.org/10.3929/ethz-b-000523822 en eng Cambridge University Press info:eu-repo/semantics/altIdentifier/doi/10.1017/jog.2021.120 info:eu-repo/semantics/altIdentifier/wos/000827708900005 info:eu-repo/grantAgreement/SNF/Projekte MINT/162444 http://hdl.handle.net/20.500.11850/523822 doi:10.3929/ethz-b-000523822 info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International CC-BY-NC-SA Journal of Glaciology, 68 (270) Glacier flow Glacier modelling Ice dynamics Ice velocity info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion 2022 ftethz https://doi.org/20.500.11850/523822 https://doi.org/10.3929/ethz-b-000523822 https://doi.org/10.1017/jog.2021.120 2023-02-13T01:07:07Z This paper introduces the Instructed Glacier Model (IGM) – a model that simulates ice dynamics, mass balance and its coupling to predict the evolution of glaciers, icefields or ice sheets. The nov elty of IGM is that it models the ice flow by a Convolutional Neural Network, which is trained from data generated with hybrid SIA + SSA or Stokes ice flow models. By doing so, the most com putationally demanding model component is substituted by a cheap emulator. Once trained with representative data, we demonstrate that IGM permits to model mountain glaciers up to 1000 × faster than Stokes ones on Central Processing Units (CPU) with fidelity levels above 90% in terms of ice flow solutions leading to nearly identical transient thickness evolution. Switching to the GPU often permits additional significant speed-ups, especially when emulating Stokes dynamics or/and modelling at high spatial resolution. IGM is an open-source Python code which deals with two-dimensional (2-D) gridded input and output data. Together with a companion library of trained ice flow emulators, IGM permits user-friendly, highly efficient and mechanically state of-the-art glacier and icefields simulations ISSN:0022-1430 ISSN:1727-5652 Article in Journal/Newspaper Journal of Glaciology ETH Zürich Research Collection |
institution |
Open Polar |
collection |
ETH Zürich Research Collection |
op_collection_id |
ftethz |
language |
English |
topic |
Glacier flow Glacier modelling Ice dynamics Ice velocity |
spellingShingle |
Glacier flow Glacier modelling Ice dynamics Ice velocity Jouvet, Guillaume Cordonnier, Guillaume Kim, Byungsoo Lüthi, Martin Vieli, Andreas Aschwanden, Andy Deep learning speeds up ice flow modelling by several orders of magnitude |
topic_facet |
Glacier flow Glacier modelling Ice dynamics Ice velocity |
description |
This paper introduces the Instructed Glacier Model (IGM) – a model that simulates ice dynamics, mass balance and its coupling to predict the evolution of glaciers, icefields or ice sheets. The nov elty of IGM is that it models the ice flow by a Convolutional Neural Network, which is trained from data generated with hybrid SIA + SSA or Stokes ice flow models. By doing so, the most com putationally demanding model component is substituted by a cheap emulator. Once trained with representative data, we demonstrate that IGM permits to model mountain glaciers up to 1000 × faster than Stokes ones on Central Processing Units (CPU) with fidelity levels above 90% in terms of ice flow solutions leading to nearly identical transient thickness evolution. Switching to the GPU often permits additional significant speed-ups, especially when emulating Stokes dynamics or/and modelling at high spatial resolution. IGM is an open-source Python code which deals with two-dimensional (2-D) gridded input and output data. Together with a companion library of trained ice flow emulators, IGM permits user-friendly, highly efficient and mechanically state of-the-art glacier and icefields simulations ISSN:0022-1430 ISSN:1727-5652 |
format |
Article in Journal/Newspaper |
author |
Jouvet, Guillaume Cordonnier, Guillaume Kim, Byungsoo Lüthi, Martin Vieli, Andreas Aschwanden, Andy |
author_facet |
Jouvet, Guillaume Cordonnier, Guillaume Kim, Byungsoo Lüthi, Martin Vieli, Andreas Aschwanden, Andy |
author_sort |
Jouvet, Guillaume |
title |
Deep learning speeds up ice flow modelling by several orders of magnitude |
title_short |
Deep learning speeds up ice flow modelling by several orders of magnitude |
title_full |
Deep learning speeds up ice flow modelling by several orders of magnitude |
title_fullStr |
Deep learning speeds up ice flow modelling by several orders of magnitude |
title_full_unstemmed |
Deep learning speeds up ice flow modelling by several orders of magnitude |
title_sort |
deep learning speeds up ice flow modelling by several orders of magnitude |
publisher |
Cambridge University Press |
publishDate |
2022 |
url |
https://hdl.handle.net/20.500.11850/523822 https://doi.org/10.3929/ethz-b-000523822 |
genre |
Journal of Glaciology |
genre_facet |
Journal of Glaciology |
op_source |
Journal of Glaciology, 68 (270) |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1017/jog.2021.120 info:eu-repo/semantics/altIdentifier/wos/000827708900005 info:eu-repo/grantAgreement/SNF/Projekte MINT/162444 http://hdl.handle.net/20.500.11850/523822 doi:10.3929/ethz-b-000523822 |
op_rights |
info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International |
op_rightsnorm |
CC-BY-NC-SA |
op_doi |
https://doi.org/20.500.11850/523822 https://doi.org/10.3929/ethz-b-000523822 https://doi.org/10.1017/jog.2021.120 |
_version_ |
1766049081628557312 |