Reservoir Computing as a Tool for Climate Predictability Studies
Reduced-order dynamical models play a central role in developing our understanding of predictability of climate irrespective of whether we are dealing with the actual climate system or surrogate climate-models. In this context, the Linear-Inverse-Modeling (LIM) approach, by capturing a few essential...
Main Author: | |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2103.06206 https://arxiv.org/abs/2103.06206 |
id |
ftdatacite:10.48550/arxiv.2103.06206 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2103.06206 2023-05-15T17:35:14+02:00 Reservoir Computing as a Tool for Climate Predictability Studies Nadiga, B. T. 2021 https://dx.doi.org/10.48550/arxiv.2103.06206 https://arxiv.org/abs/2103.06206 unknown arXiv https://dx.doi.org/10.1029/2020ms002290 arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Geophysics physics.geo-ph Machine Learning cs.LG Chaotic Dynamics nlin.CD Data Analysis, Statistics and Probability physics.data-an Machine Learning stat.ML FOS Physical sciences FOS Computer and information sciences article-journal Article ScholarlyArticle Text 2021 ftdatacite https://doi.org/10.48550/arxiv.2103.06206 https://doi.org/10.1029/2020ms002290 2022-03-10T14:27:09Z Reduced-order dynamical models play a central role in developing our understanding of predictability of climate irrespective of whether we are dealing with the actual climate system or surrogate climate-models. In this context, the Linear-Inverse-Modeling (LIM) approach, by capturing a few essential interactions between dynamical components of the full system, has proven valuable in providing insights into predictability of the full system. We demonstrate that Reservoir Computing (RC), a form of learning suitable for systems with chaotic dynamics, provides an alternative nonlinear approach that improves on the predictive skill of the LIM approach. We do this in the example setting of predicting sea-surface-temperature in the North Atlantic in the pre-industrial control simulation of a popular earth system model, the Community-Earth-System-Model so that we can compare the performance of the new RC based approach with the traditional LIM approach both when learning data is plentiful and when such data is more limited. The improved predictive skill of the RC approach over a wide range of conditions -- larger number of retained EOF coefficients, extending well into the limited data regime, etc. -- suggests that this machine-learning technique may have a use in climate predictability studies. While the possibility of developing a climate emulator -- the ability to continue the evolution of the system on the attractor long after failing to be able to track the reference trajectory -- is demonstrated in the Lorenz-63 system, it is suggested that further development of the RC approach may permit such uses of the new approach in more realistic predictability studies. : 31 pages with 12 figures Article in Journal/Newspaper North Atlantic 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 |
Geophysics physics.geo-ph Machine Learning cs.LG Chaotic Dynamics nlin.CD Data Analysis, Statistics and Probability physics.data-an Machine Learning stat.ML FOS Physical sciences FOS Computer and information sciences |
spellingShingle |
Geophysics physics.geo-ph Machine Learning cs.LG Chaotic Dynamics nlin.CD Data Analysis, Statistics and Probability physics.data-an Machine Learning stat.ML FOS Physical sciences FOS Computer and information sciences Nadiga, B. T. Reservoir Computing as a Tool for Climate Predictability Studies |
topic_facet |
Geophysics physics.geo-ph Machine Learning cs.LG Chaotic Dynamics nlin.CD Data Analysis, Statistics and Probability physics.data-an Machine Learning stat.ML FOS Physical sciences FOS Computer and information sciences |
description |
Reduced-order dynamical models play a central role in developing our understanding of predictability of climate irrespective of whether we are dealing with the actual climate system or surrogate climate-models. In this context, the Linear-Inverse-Modeling (LIM) approach, by capturing a few essential interactions between dynamical components of the full system, has proven valuable in providing insights into predictability of the full system. We demonstrate that Reservoir Computing (RC), a form of learning suitable for systems with chaotic dynamics, provides an alternative nonlinear approach that improves on the predictive skill of the LIM approach. We do this in the example setting of predicting sea-surface-temperature in the North Atlantic in the pre-industrial control simulation of a popular earth system model, the Community-Earth-System-Model so that we can compare the performance of the new RC based approach with the traditional LIM approach both when learning data is plentiful and when such data is more limited. The improved predictive skill of the RC approach over a wide range of conditions -- larger number of retained EOF coefficients, extending well into the limited data regime, etc. -- suggests that this machine-learning technique may have a use in climate predictability studies. While the possibility of developing a climate emulator -- the ability to continue the evolution of the system on the attractor long after failing to be able to track the reference trajectory -- is demonstrated in the Lorenz-63 system, it is suggested that further development of the RC approach may permit such uses of the new approach in more realistic predictability studies. : 31 pages with 12 figures |
format |
Article in Journal/Newspaper |
author |
Nadiga, B. T. |
author_facet |
Nadiga, B. T. |
author_sort |
Nadiga, B. T. |
title |
Reservoir Computing as a Tool for Climate Predictability Studies |
title_short |
Reservoir Computing as a Tool for Climate Predictability Studies |
title_full |
Reservoir Computing as a Tool for Climate Predictability Studies |
title_fullStr |
Reservoir Computing as a Tool for Climate Predictability Studies |
title_full_unstemmed |
Reservoir Computing as a Tool for Climate Predictability Studies |
title_sort |
reservoir computing as a tool for climate predictability studies |
publisher |
arXiv |
publishDate |
2021 |
url |
https://dx.doi.org/10.48550/arxiv.2103.06206 https://arxiv.org/abs/2103.06206 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_relation |
https://dx.doi.org/10.1029/2020ms002290 |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2103.06206 https://doi.org/10.1029/2020ms002290 |
_version_ |
1766134331655323648 |