Interpretable Structural Model Error Discovery From Sparse Assimilation Increments Using Spectral Bias-Reduced Neural Networks: A Quasi-Geostrophic Turbulence Test Case

Simple item page
dc.citation.articleNumbere2023MS004033en_US
dc.citation.issueNumber3en_US
dc.citation.journalTitleJournal of Advances in Modeling Earth Systemsen_US
dc.citation.volumeNumber16en_US
dc.contributor.authorMojgani, Ramboden_US
dc.contributor.authorChattopadhyay, Asheshen_US
dc.contributor.authorHassanzadeh, Pedramen_US
dc.date.accessioned2024-08-09T16:25:24Zen_US
dc.date.available2024-08-09T16:25:24Zen_US
dc.date.issued2024en_US
dc.description.abstractEarth system models suffer from various structural and parametric errors in their representation of nonlinear, multi-scale processes, leading to uncertainties in their long-term projections. The effects of many of these errors (particularly those due to fast physics) can be quantified in short-term simulations, for example, as differences between the predicted and observed states (analysis increments). With the increase in the availability of high-quality observations and simulations, learning nudging from these increments to correct model errors has become an active research area. However, most studies focus on using neural networks, which while powerful, are hard to interpret, are data-hungry, and poorly generalize out-of-distribution. Here, we show the capabilities of Model Error Discovery with Interpretability and Data Assimilation (MEDIDA), a general, data-efficient framework that uses sparsity-promoting equation-discovery techniques to learn model errors from analysis increments. Using two-layer quasi-geostrophic turbulence as the test case, MEDIDA is shown to successfully discover various linear and nonlinear structural/parametric errors when full observations are available. Discovery from spatially sparse observations is found to require highly accurate interpolation schemes. While NNs have shown success as interpolators in recent studies, here, they are found inadequate due to their inability to accurately represent small scales, a phenomenon known as spectral bias. We show that a general remedy, adding a random Fourier feature layer to the NN, resolves this issue enabling MEDIDA to successfully discover model errors from sparse observations. These promising results suggest that with further development, MEDIDA could be scaled up to models of the Earth system and real observations.en_US
dc.identifier.citationMojgani, R., Chattopadhyay, A., & Hassanzadeh, P. (2024). Interpretable Structural Model Error Discovery From Sparse Assimilation Increments Using Spectral Bias-Reduced Neural Networks: A Quasi-Geostrophic Turbulence Test Case. Journal of Advances in Modeling Earth Systems, 16(3), e2023MS004033. https://doi.org/10.1029/2023MS004033en_US
dc.identifier.digitalInterpretable-Structural-Model-Erroren_US
dc.identifier.doihttps://doi.org/10.1029/2023MS004033en_US
dc.identifier.urihttps://hdl.handle.net/1911/117624en_US
dc.language.isoengen_US
dc.publisherWileyen_US
dc.rightsExcept where otherwise noted, this work is licensed under a Creative Commons Attribution (CC BY) license.  Permission to reuse, publish, or reproduce the work beyond the terms of the license or beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.titleInterpretable Structural Model Error Discovery From Sparse Assimilation Increments Using Spectral Bias-Reduced Neural Networks: A Quasi-Geostrophic Turbulence Test Caseen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Interpretable-Structural-Model-Error.pdf
Size:
2.24 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
Earth, Environmental and Planetary Sciences Publications
Mechanical Engineering Publications