Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ...
Modeling is crucial to understanding the effect of greenhouse gases, warming, and ice sheet melting on the ocean. At the same time, ocean processes affect phenomena such as hurricanes and droughts. Parameters in the models that cannot be physically measured have a significant effect on the model out...
Main Authors: | , , , , , , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2311.08421 https://arxiv.org/abs/2311.08421 |
id |
ftdatacite:10.48550/arxiv.2311.08421 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2311.08421 2023-12-31T10:08:01+01:00 Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ... Sun, Yixuan Cucuzzella, Elizabeth Brus, Steven Narayanan, Sri Hari Krishna Nadiga, Balu Van Roekel, Luke Hückelheim, Jan Madireddy, Sandeep 2023 https://dx.doi.org/10.48550/arxiv.2311.08421 https://arxiv.org/abs/2311.08421 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences CreativeWork Preprint article Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2311.08421 2023-12-01T11:10:41Z Modeling is crucial to understanding the effect of greenhouse gases, warming, and ice sheet melting on the ocean. At the same time, ocean processes affect phenomena such as hurricanes and droughts. Parameters in the models that cannot be physically measured have a significant effect on the model output. For an idealized ocean model, we generated perturbed parameter ensemble data and trained surrogate neural network models. The neural surrogates accurately predicted the one-step forward dynamics, of which we then computed the parametric sensitivity. ... Report Ice Sheet DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences |
spellingShingle |
Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences Sun, Yixuan Cucuzzella, Elizabeth Brus, Steven Narayanan, Sri Hari Krishna Nadiga, Balu Van Roekel, Luke Hückelheim, Jan Madireddy, Sandeep Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ... |
topic_facet |
Atmospheric and Oceanic Physics physics.ao-ph Machine Learning cs.LG FOS Physical sciences FOS Computer and information sciences |
description |
Modeling is crucial to understanding the effect of greenhouse gases, warming, and ice sheet melting on the ocean. At the same time, ocean processes affect phenomena such as hurricanes and droughts. Parameters in the models that cannot be physically measured have a significant effect on the model output. For an idealized ocean model, we generated perturbed parameter ensemble data and trained surrogate neural network models. The neural surrogates accurately predicted the one-step forward dynamics, of which we then computed the parametric sensitivity. ... |
format |
Report |
author |
Sun, Yixuan Cucuzzella, Elizabeth Brus, Steven Narayanan, Sri Hari Krishna Nadiga, Balu Van Roekel, Luke Hückelheim, Jan Madireddy, Sandeep |
author_facet |
Sun, Yixuan Cucuzzella, Elizabeth Brus, Steven Narayanan, Sri Hari Krishna Nadiga, Balu Van Roekel, Luke Hückelheim, Jan Madireddy, Sandeep |
author_sort |
Sun, Yixuan |
title |
Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ... |
title_short |
Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ... |
title_full |
Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ... |
title_fullStr |
Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ... |
title_full_unstemmed |
Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models ... |
title_sort |
surrogate neural networks to estimate parametric sensitivity of ocean models ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2311.08421 https://arxiv.org/abs/2311.08421 |
genre |
Ice Sheet |
genre_facet |
Ice Sheet |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2311.08421 |
_version_ |
1786840567419764736 |