Ice-flow model emulator based on physics-informed deep learning
Convolutional neural networks (CNN) trained from high-order ice-flow model realisations have proven to be outstanding emulators in terms of fidelity and computational performance. However, the dependence on an ensemble of realisations of an instructor model renders this strategy difficult to general...
Published in: | Journal of Glaciology |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Cambridge University Press
|
Subjects: | |
Online Access: | https://doi.org/10.1017/jog.2023.73 https://doaj.org/article/4a5a316da97843df8b6d9bd5b32a17c6 |
id |
ftdoajarticles:oai:doaj.org/article:4a5a316da97843df8b6d9bd5b32a17c6 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:4a5a316da97843df8b6d9bd5b32a17c6 2023-10-29T02:37:09+01:00 Ice-flow model emulator based on physics-informed deep learning Guillaume Jouvet Guillaume Cordonnier https://doi.org/10.1017/jog.2023.73 https://doaj.org/article/4a5a316da97843df8b6d9bd5b32a17c6 EN eng Cambridge University Press https://www.cambridge.org/core/product/identifier/S0022143023000734/type/journal_article https://doaj.org/toc/0022-1430 https://doaj.org/toc/1727-5652 doi:10.1017/jog.2023.73 0022-1430 1727-5652 https://doaj.org/article/4a5a316da97843df8b6d9bd5b32a17c6 Journal of Glaciology, Pp 1-15 glacier flow glacier modelling glacier mechanics ice-sheet modelling Environmental sciences GE1-350 Meteorology. Climatology QC851-999 article ftdoajarticles https://doi.org/10.1017/jog.2023.73 2023-10-01T00:40:48Z Convolutional neural networks (CNN) trained from high-order ice-flow model realisations have proven to be outstanding emulators in terms of fidelity and computational performance. However, the dependence on an ensemble of realisations of an instructor model renders this strategy difficult to generalise to a variety of ice-flow regimes found in the nature. To overcome this issue, we adopt the approach of physics-informed deep learning, which fuses traditional numerical solutions by finite differences/elements and deep-learning approaches. Here, we train a CNN to minimise the energy associated with high-order ice-flow equations within the time iterations of a glacier evolution model. As a result, our emulator is a promising alternative to traditional solvers thanks to its high computational efficiency (especially on GPU), its high fidelity to the original model, its simplified training (without requiring any data), its capability to handle a variety of ice-flow regimes and memorise previous solutions, and its relatively simple implementation. Embedded into the ‘Instructed Glacier Model’ (IGM) framework, the potential of the emulator is illustrated with three applications including a large-scale high-resolution (2400x4000) forward glacier evolution model, an inverse modelling case for data assimilation, and an ice shelf. Article in Journal/Newspaper Ice Sheet Ice Shelf Journal of Glaciology Directory of Open Access Journals: DOAJ Articles Journal of Glaciology 1 15 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
glacier flow glacier modelling glacier mechanics ice-sheet modelling Environmental sciences GE1-350 Meteorology. Climatology QC851-999 |
spellingShingle |
glacier flow glacier modelling glacier mechanics ice-sheet modelling Environmental sciences GE1-350 Meteorology. Climatology QC851-999 Guillaume Jouvet Guillaume Cordonnier Ice-flow model emulator based on physics-informed deep learning |
topic_facet |
glacier flow glacier modelling glacier mechanics ice-sheet modelling Environmental sciences GE1-350 Meteorology. Climatology QC851-999 |
description |
Convolutional neural networks (CNN) trained from high-order ice-flow model realisations have proven to be outstanding emulators in terms of fidelity and computational performance. However, the dependence on an ensemble of realisations of an instructor model renders this strategy difficult to generalise to a variety of ice-flow regimes found in the nature. To overcome this issue, we adopt the approach of physics-informed deep learning, which fuses traditional numerical solutions by finite differences/elements and deep-learning approaches. Here, we train a CNN to minimise the energy associated with high-order ice-flow equations within the time iterations of a glacier evolution model. As a result, our emulator is a promising alternative to traditional solvers thanks to its high computational efficiency (especially on GPU), its high fidelity to the original model, its simplified training (without requiring any data), its capability to handle a variety of ice-flow regimes and memorise previous solutions, and its relatively simple implementation. Embedded into the ‘Instructed Glacier Model’ (IGM) framework, the potential of the emulator is illustrated with three applications including a large-scale high-resolution (2400x4000) forward glacier evolution model, an inverse modelling case for data assimilation, and an ice shelf. |
format |
Article in Journal/Newspaper |
author |
Guillaume Jouvet Guillaume Cordonnier |
author_facet |
Guillaume Jouvet Guillaume Cordonnier |
author_sort |
Guillaume Jouvet |
title |
Ice-flow model emulator based on physics-informed deep learning |
title_short |
Ice-flow model emulator based on physics-informed deep learning |
title_full |
Ice-flow model emulator based on physics-informed deep learning |
title_fullStr |
Ice-flow model emulator based on physics-informed deep learning |
title_full_unstemmed |
Ice-flow model emulator based on physics-informed deep learning |
title_sort |
ice-flow model emulator based on physics-informed deep learning |
publisher |
Cambridge University Press |
url |
https://doi.org/10.1017/jog.2023.73 https://doaj.org/article/4a5a316da97843df8b6d9bd5b32a17c6 |
genre |
Ice Sheet Ice Shelf Journal of Glaciology |
genre_facet |
Ice Sheet Ice Shelf Journal of Glaciology |
op_source |
Journal of Glaciology, Pp 1-15 |
op_relation |
https://www.cambridge.org/core/product/identifier/S0022143023000734/type/journal_article https://doaj.org/toc/0022-1430 https://doaj.org/toc/1727-5652 doi:10.1017/jog.2023.73 0022-1430 1727-5652 https://doaj.org/article/4a5a316da97843df8b6d9bd5b32a17c6 |
op_doi |
https://doi.org/10.1017/jog.2023.73 |
container_title |
Journal of Glaciology |
container_start_page |
1 |
op_container_end_page |
15 |
_version_ |
1781061559608410112 |