Deep learning speeds up ice flow modelling by several orders of magnitude
International audience 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, whi...
Published in: | Journal of Glaciology |
---|---|
Main Authors: | , , , , , |
Other Authors: | , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2021
|
Subjects: | |
Online Access: | https://hal.inria.fr/hal-03525458 https://hal.inria.fr/hal-03525458/document https://hal.inria.fr/hal-03525458/file/JOG-21-0059.pdf https://doi.org/10.1017/jog.2021.120 |
id |
ftccsdartic:oai:HAL:hal-03525458v1 |
---|---|
record_format |
openpolar |
spelling |
ftccsdartic:oai:HAL:hal-03525458v1 2023-05-15T16:57:28+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 Department of Geography Zürich Universität Zürich Zürich = University of Zurich (UZH) GRAPHics and DEsign with hEterogeneous COntent (GRAPHDECO) Inria Sophia Antipolis - Méditerranée (CRISAM) Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria) Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology Zürich (ETH Zürich) Geophysical Institute Fairbanks University of Alaska Fairbanks (UAF) 2021-12-22 https://hal.inria.fr/hal-03525458 https://hal.inria.fr/hal-03525458/document https://hal.inria.fr/hal-03525458/file/JOG-21-0059.pdf https://doi.org/10.1017/jog.2021.120 en eng HAL CCSD International Glaciological Society info:eu-repo/semantics/altIdentifier/doi/10.1017/jog.2021.120 hal-03525458 https://hal.inria.fr/hal-03525458 https://hal.inria.fr/hal-03525458/document https://hal.inria.fr/hal-03525458/file/JOG-21-0059.pdf doi:10.1017/jog.2021.120 info:eu-repo/semantics/OpenAccess ISSN: 0022-1430 EISSN: 1727-5652 Journal of Glaciology https://hal.inria.fr/hal-03525458 Journal of Glaciology, In press, pp.1-14. ⟨10.1017/jog.2021.120⟩ [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] info:eu-repo/semantics/article Journal articles 2021 ftccsdartic https://doi.org/10.1017/jog.2021.120 2023-03-19T05:33:43Z International audience 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 Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) Journal of Glaciology 1 14 |
institution |
Open Polar |
collection |
Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
op_collection_id |
ftccsdartic |
language |
English |
topic |
[SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
spellingShingle |
[SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] 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 |
[SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
description |
International audience 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. |
author2 |
Department of Geography Zürich Universität Zürich Zürich = University of Zurich (UZH) GRAPHics and DEsign with hEterogeneous COntent (GRAPHDECO) Inria Sophia Antipolis - Méditerranée (CRISAM) Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria) Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology Zürich (ETH Zürich) Geophysical Institute Fairbanks University of Alaska Fairbanks (UAF) |
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 |
HAL CCSD |
publishDate |
2021 |
url |
https://hal.inria.fr/hal-03525458 https://hal.inria.fr/hal-03525458/document https://hal.inria.fr/hal-03525458/file/JOG-21-0059.pdf https://doi.org/10.1017/jog.2021.120 |
genre |
Journal of Glaciology |
genre_facet |
Journal of Glaciology |
op_source |
ISSN: 0022-1430 EISSN: 1727-5652 Journal of Glaciology https://hal.inria.fr/hal-03525458 Journal of Glaciology, In press, pp.1-14. ⟨10.1017/jog.2021.120⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1017/jog.2021.120 hal-03525458 https://hal.inria.fr/hal-03525458 https://hal.inria.fr/hal-03525458/document https://hal.inria.fr/hal-03525458/file/JOG-21-0059.pdf doi:10.1017/jog.2021.120 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1017/jog.2021.120 |
container_title |
Journal of Glaciology |
container_start_page |
1 |
op_container_end_page |
14 |
_version_ |
1766049016544493568 |