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 novelty of IGM is that it models the ice flow by a Convolutional Neural Network, which is trained from data...
Published in: | Journal of Glaciology |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Cambridge University Press
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1017/jog.2021.120 https://doaj.org/article/242843af6c0f4ed9bc0503b7d509553c |
id |
ftdoajarticles:oai:doaj.org/article:242843af6c0f4ed9bc0503b7d509553c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:242843af6c0f4ed9bc0503b7d509553c 2023-05-15T16:57:33+02:00 Deep learning speeds up ice flow modelling by several orders of magnitude Guillaume Jouvet Guillaume Cordonnier Byungsoo Kim Martin Lüthi Andreas Vieli Andy Aschwanden 2022-08-01T00:00:00Z https://doi.org/10.1017/jog.2021.120 https://doaj.org/article/242843af6c0f4ed9bc0503b7d509553c EN eng Cambridge University Press https://www.cambridge.org/core/product/identifier/S0022143021001209/type/journal_article https://doaj.org/toc/0022-1430 https://doaj.org/toc/1727-5652 doi:10.1017/jog.2021.120 0022-1430 1727-5652 https://doaj.org/article/242843af6c0f4ed9bc0503b7d509553c Journal of Glaciology, Vol 68, Pp 651-664 (2022) Glacier flow glacier modelling ice dynamics ice velocity Environmental sciences GE1-350 Meteorology. Climatology QC851-999 article 2022 ftdoajarticles https://doi.org/10.1017/jog.2021.120 2023-03-12T01:30:54Z 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 novelty 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 computationally 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. Article in Journal/Newspaper Journal of Glaciology Directory of Open Access Journals: DOAJ Articles Journal of Glaciology 68 270 651 664 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Glacier flow glacier modelling ice dynamics ice velocity Environmental sciences GE1-350 Meteorology. Climatology QC851-999 |
spellingShingle |
Glacier flow glacier modelling ice dynamics ice velocity Environmental sciences GE1-350 Meteorology. Climatology QC851-999 Guillaume Jouvet Guillaume Cordonnier Byungsoo Kim Martin Lüthi Andreas Vieli Andy Aschwanden Deep learning speeds up ice flow modelling by several orders of magnitude |
topic_facet |
Glacier flow glacier modelling ice dynamics ice velocity Environmental sciences GE1-350 Meteorology. Climatology QC851-999 |
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 novelty 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 computationally 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. |
format |
Article in Journal/Newspaper |
author |
Guillaume Jouvet Guillaume Cordonnier Byungsoo Kim Martin Lüthi Andreas Vieli Andy Aschwanden |
author_facet |
Guillaume Jouvet Guillaume Cordonnier Byungsoo Kim Martin Lüthi Andreas Vieli Andy Aschwanden |
author_sort |
Guillaume Jouvet |
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://doi.org/10.1017/jog.2021.120 https://doaj.org/article/242843af6c0f4ed9bc0503b7d509553c |
genre |
Journal of Glaciology |
genre_facet |
Journal of Glaciology |
op_source |
Journal of Glaciology, Vol 68, Pp 651-664 (2022) |
op_relation |
https://www.cambridge.org/core/product/identifier/S0022143021001209/type/journal_article https://doaj.org/toc/0022-1430 https://doaj.org/toc/1727-5652 doi:10.1017/jog.2021.120 0022-1430 1727-5652 https://doaj.org/article/242843af6c0f4ed9bc0503b7d509553c |
op_doi |
https://doi.org/10.1017/jog.2021.120 |
container_title |
Journal of Glaciology |
container_volume |
68 |
container_issue |
270 |
container_start_page |
651 |
op_container_end_page |
664 |
_version_ |
1766049120808599552 |