WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture
Ocean surface waves play an important role in maintaining the marginal ice zone, a heterogenous region occupied by sea ice floes with variable horizontal sizes. The location, width, and evolution of the marginal ice zone are determined by the mutual interaction of ocean waves and floes, as waves pro...
Published in: | Geoscientific Model Development |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2022
|
Subjects: | |
Online Access: | https://doi.org/10.5194/gmd-15-803-2022 https://doaj.org/article/cdd02083c978423f9ae3b57c6b6c09f0 |
id |
ftdoajarticles:oai:doaj.org/article:cdd02083c978423f9ae3b57c6b6c09f0 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:cdd02083c978423f9ae3b57c6b6c09f0 2023-05-15T18:16:36+02:00 WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture C. Horvat L. A. Roach 2022-01-01T00:00:00Z https://doi.org/10.5194/gmd-15-803-2022 https://doaj.org/article/cdd02083c978423f9ae3b57c6b6c09f0 EN eng Copernicus Publications https://gmd.copernicus.org/articles/15/803/2022/gmd-15-803-2022.pdf https://doaj.org/toc/1991-959X https://doaj.org/toc/1991-9603 doi:10.5194/gmd-15-803-2022 1991-959X 1991-9603 https://doaj.org/article/cdd02083c978423f9ae3b57c6b6c09f0 Geoscientific Model Development, Vol 15, Pp 803-814 (2022) Geology QE1-996.5 article 2022 ftdoajarticles https://doi.org/10.5194/gmd-15-803-2022 2022-12-31T10:49:34Z Ocean surface waves play an important role in maintaining the marginal ice zone, a heterogenous region occupied by sea ice floes with variable horizontal sizes. The location, width, and evolution of the marginal ice zone are determined by the mutual interaction of ocean waves and floes, as waves propagate into the ice, bend it, and fracture it. In previous work, we developed a one-dimensional “superparameterized” scheme to simulate the interaction between the stochastic ocean surface wave field and sea ice. As this method is computationally expensive and not bitwise reproducible, here we use a pair of neural networks to accelerate this parameterization, delivering an adaptable, computationally inexpensive, reproducible approach for simulating stochastic wave–ice interactions. Implemented in the sea ice model CICE, this accelerated code reproduces global statistics resulting from the full wave fracture code without increasing computational overheads. The combined model, Wave-Induced Floe Fracture (WIFF v1.0), is publicly available and may be incorporated into climate models that seek to represent the effect of waves fracturing sea ice. Article in Journal/Newspaper Sea ice Directory of Open Access Journals: DOAJ Articles Geoscientific Model Development 15 2 803 814 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Geology QE1-996.5 |
spellingShingle |
Geology QE1-996.5 C. Horvat L. A. Roach WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture |
topic_facet |
Geology QE1-996.5 |
description |
Ocean surface waves play an important role in maintaining the marginal ice zone, a heterogenous region occupied by sea ice floes with variable horizontal sizes. The location, width, and evolution of the marginal ice zone are determined by the mutual interaction of ocean waves and floes, as waves propagate into the ice, bend it, and fracture it. In previous work, we developed a one-dimensional “superparameterized” scheme to simulate the interaction between the stochastic ocean surface wave field and sea ice. As this method is computationally expensive and not bitwise reproducible, here we use a pair of neural networks to accelerate this parameterization, delivering an adaptable, computationally inexpensive, reproducible approach for simulating stochastic wave–ice interactions. Implemented in the sea ice model CICE, this accelerated code reproduces global statistics resulting from the full wave fracture code without increasing computational overheads. The combined model, Wave-Induced Floe Fracture (WIFF v1.0), is publicly available and may be incorporated into climate models that seek to represent the effect of waves fracturing sea ice. |
format |
Article in Journal/Newspaper |
author |
C. Horvat L. A. Roach |
author_facet |
C. Horvat L. A. Roach |
author_sort |
C. Horvat |
title |
WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture |
title_short |
WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture |
title_full |
WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture |
title_fullStr |
WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture |
title_full_unstemmed |
WIFF1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture |
title_sort |
wiff1.0: a hybrid machine-learning-based parameterization of wave-induced sea ice floe fracture |
publisher |
Copernicus Publications |
publishDate |
2022 |
url |
https://doi.org/10.5194/gmd-15-803-2022 https://doaj.org/article/cdd02083c978423f9ae3b57c6b6c09f0 |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Geoscientific Model Development, Vol 15, Pp 803-814 (2022) |
op_relation |
https://gmd.copernicus.org/articles/15/803/2022/gmd-15-803-2022.pdf https://doaj.org/toc/1991-959X https://doaj.org/toc/1991-9603 doi:10.5194/gmd-15-803-2022 1991-959X 1991-9603 https://doaj.org/article/cdd02083c978423f9ae3b57c6b6c09f0 |
op_doi |
https://doi.org/10.5194/gmd-15-803-2022 |
container_title |
Geoscientific Model Development |
container_volume |
15 |
container_issue |
2 |
container_start_page |
803 |
op_container_end_page |
814 |
_version_ |
1766190334737383424 |