A Physics-Informed Auto-Learning Framework for Developing Stochastic Conceptual Models for ENSO Diversity.
Saved in:
| Title: | A Physics-Informed Auto-Learning Framework for Developing Stochastic Conceptual Models for ENSO Diversity. |
|---|---|
| Authors: | Zhang, Yinling1 (AUTHOR), Chen, Nan1 (AUTHOR) chennan@math.wisc.edu, Vialard, Jérôme2 (AUTHOR), Fang, Xianghui3 (AUTHOR) |
| Source: | Journal of Climate. Dec2024, Vol. 37 Issue 23, p6323-6347. 25p. |
| Subjects: | Machine learning, Stochastic learning models, El Niño, Ocean temperature, Nonlinear regression |
| Abstract: | Understanding El Niño–Southern Oscillation (ENSO) dynamics has tremendously improved over the past few decades. The ENSO diversity in spatial pattern, peak intensity, and temporal evolution is, however, still poorly represented in conceptual ENSO models. In this paper, a physics-informed auto-learning framework is applied to derive ENSO stochastic conceptual models with varying degrees of freedom. The framework is computationally efficient and easy to apply. Once the state vector of the target model is set, causal inference is exploited to build the right-hand side of the equations based on a mathematical function library. Fundamentally different from standard nonlinear regression, the auto-learning framework provides a parsimonious model by retaining only terms that improve the dynamical consistency with observations. It can also identify crucial latent variables and provide physical explanations. This methodology successfully reconstructs the equations of a realistic six-dimensional reference ENSO model based on the recharge oscillator theory from its data. A hierarchy of lower-dimensional models is derived, and their representation of ENSO (including its diversity) is systematically assessed. The minimum model that represents ENSO diversity is four-dimensional, with three interannual variables describing the western Pacific thermocline depth, the eastern and central Pacific sea surface temperatures (SSTs), and one intraseasonal variable for westerly wind events. Without the intraseasonal variable, the resulting three-dimensional model underestimates extreme events and is too regular. A limited number of weak nonlinearities in the model are essential in reproducing the observed extreme El Niño events and the observed nonlinear relationship between eastern and western Pacific SSTs. Significance Statement: This study develops a physics-informed auto-learning approach to improve the modeling and understanding of El Niño–Southern Oscillation (ENSO), a major climate phenomenon influencing global weather and climate. The auto-learning framework explores the causality between key processes to systematically produce stochastic conceptual models with different climate factors that simulate the diversity of observed ENSO events. The key finding is that the minimal model for characterizing the ENSO diversity (with the least number of climate factors) is a four-variable model capturing thermocline depth, sea surface temperatures, and wind bursts that can reproduce intensity and spatial pattern variation. This advancement provides an interpretable tool to identify the minimum sufficient processes governing ENSO behavior for improved predictability. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Climate is the property of American Meteorological Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 180762938 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A Physics-Informed Auto-Learning Framework for Developing Stochastic Conceptual Models for ENSO Diversity. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Yinling%22">Zhang, Yinling</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Nan%22">Chen, Nan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> chennan@math.wisc.edu</i><br /><searchLink fieldCode="AR" term="%22Vialard%2C+Jérôme%22">Vialard, Jérôme</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Fang%2C+Xianghui%22">Fang, Xianghui</searchLink><relatesTo>3</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Climate%22">Journal of Climate</searchLink>. Dec2024, Vol. 37 Issue 23, p6323-6347. 25p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+learning+models%22">Stochastic learning models</searchLink><br /><searchLink fieldCode="DE" term="%22El+Niño%22">El Niño</searchLink><br /><searchLink fieldCode="DE" term="%22Ocean+temperature%22">Ocean temperature</searchLink><br /><searchLink fieldCode="DE" term="%22Nonlinear+regression%22">Nonlinear regression</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Understanding El Niño–Southern Oscillation (ENSO) dynamics has tremendously improved over the past few decades. The ENSO diversity in spatial pattern, peak intensity, and temporal evolution is, however, still poorly represented in conceptual ENSO models. In this paper, a physics-informed auto-learning framework is applied to derive ENSO stochastic conceptual models with varying degrees of freedom. The framework is computationally efficient and easy to apply. Once the state vector of the target model is set, causal inference is exploited to build the right-hand side of the equations based on a mathematical function library. Fundamentally different from standard nonlinear regression, the auto-learning framework provides a parsimonious model by retaining only terms that improve the dynamical consistency with observations. It can also identify crucial latent variables and provide physical explanations. This methodology successfully reconstructs the equations of a realistic six-dimensional reference ENSO model based on the recharge oscillator theory from its data. A hierarchy of lower-dimensional models is derived, and their representation of ENSO (including its diversity) is systematically assessed. The minimum model that represents ENSO diversity is four-dimensional, with three interannual variables describing the western Pacific thermocline depth, the eastern and central Pacific sea surface temperatures (SSTs), and one intraseasonal variable for westerly wind events. Without the intraseasonal variable, the resulting three-dimensional model underestimates extreme events and is too regular. A limited number of weak nonlinearities in the model are essential in reproducing the observed extreme El Niño events and the observed nonlinear relationship between eastern and western Pacific SSTs. Significance Statement: This study develops a physics-informed auto-learning approach to improve the modeling and understanding of El Niño–Southern Oscillation (ENSO), a major climate phenomenon influencing global weather and climate. The auto-learning framework explores the causality between key processes to systematically produce stochastic conceptual models with different climate factors that simulate the diversity of observed ENSO events. The key finding is that the minimal model for characterizing the ENSO diversity (with the least number of climate factors) is a four-variable model capturing thermocline depth, sea surface temperatures, and wind bursts that can reproduce intensity and spatial pattern variation. This advancement provides an interpretable tool to identify the minimum sufficient processes governing ENSO behavior for improved predictability. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Climate is the property of American Meteorological Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=180762938 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1175/JCLI-D-24-0092.1 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 25 StartPage: 6323 Subjects: – SubjectFull: Machine learning Type: general – SubjectFull: Stochastic learning models Type: general – SubjectFull: El Niño Type: general – SubjectFull: Ocean temperature Type: general – SubjectFull: Nonlinear regression Type: general Titles: – TitleFull: A Physics-Informed Auto-Learning Framework for Developing Stochastic Conceptual Models for ENSO Diversity. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhang, Yinling – PersonEntity: Name: NameFull: Chen, Nan – PersonEntity: Name: NameFull: Vialard, Jérôme – PersonEntity: Name: NameFull: Fang, Xianghui IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 08948755 Numbering: – Type: volume Value: 37 – Type: issue Value: 23 Titles: – TitleFull: Journal of Climate Type: main |
| ResultId | 1 |
