Benchmarking of machine learning ocean subgrid parameterizations in an idealized model

Ross, Andrew Slavin; Perezhogin, Pavel; Fernandez‐Granda, Carlos; Zanna, Laure

doi:10.1002/essoar.10511742.2

Cited by 3 publications

(1 citation statement)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Version 1.0.2 of the Python repository used for training and evaluating parameterizations is preserved at https:// doi.org/10.5281/zenodo.7222704, available via the MIT license and developed openly at https://github.com/ m2lines/pyqg_parameterization_benchmarks (Ross et al, 2022). The baseline high-and low-resolution datasets used for evaluating parameterizations, as well as the subgrid forcing data sets used for training them, are available at Zenodo via https://doi.org/10.5281/zenodo.6609034 under a Creative Commons Attribution 4.0 International license (Ross, 2022).…”

Section: Appendix A: Baseline Local Physical Parameterizations A1 Sma...mentioning

confidence: 99%

Benchmarking of Machine Learning Ocean Subgrid Parameterizations in an Idealized Model

Ross

Perezhogin

Fernandez‐Granda

et al. 2023

J Adv Model Earth Syst

Self Cite

View full text Add to dashboard Cite

Current state-of-the-art climate models solve geophysical fluid equations on horizontal grids of size 25 km and coarser. Models at this resolution are not able to accurately and sufficiently resolve processes with physical length scales smaller than the model grid, for example, convection in the atmosphere and mesoscale eddies in the ocean. Since increases in computational power will likely not enable climate models to resolve these processes before the effects of climate change ensue (Fox-Kemper et al., 2014;Schneider et al., 2017), we must represent subgrid-scale (SGS) processes with closure models, also known as parameterizations. Yet, these SGS models are some of the largest sources of bias and uncertainties in climate simulations: for example, insufficient representations of transient eddies cause biases in modeled currents and sea surface temperature in the ocean (Griffies et al., 2015;Hewitt et al., 2020), and the precipitation pattern is strongly sensitive to the different subgrid cloud closures, thereby causing significant errors in climate projections (Stevens & Bony, 2013). Therefore, developing robust parameterizations remains an important task toward reliable climate projections.

show abstract

Section: Appendix A: Baseline Local Physical Parameterizations A1 Sma...mentioning

confidence: 99%

Benchmarking of Machine Learning Ocean Subgrid Parameterizations in an Idealized Model

Ross

Perezhogin

Fernandez‐Granda

et al. 2023

J Adv Model Earth Syst

Self Cite

View full text Add to dashboard Cite

show abstract

Graph Networks as Inductive Bias for Genetic Programming: Symbolic Models for Particle-Laden Flows

Reuter¹,

Hani²,

Evrard³

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A transformer-based convolutional method to model inverse cascade in forced two-dimensional turbulence

Li,

Xie,

Zhang

et al. 2025

Journal of Computational Physics

View full text Add to dashboard Cite

Benchmarking of machine learning ocean subgrid parameterizations in an idealized model

Abstract: This a preprint and has not been peer reviewed. Data may be preliminary.

Cited by 3 publications

References 77 publications

Benchmarking of Machine Learning Ocean Subgrid Parameterizations in an Idealized Model

Benchmarking of Machine Learning Ocean Subgrid Parameterizations in an Idealized Model

Graph Networks as Inductive Bias for Genetic Programming: Symbolic Models for Particle-Laden Flows

A transformer-based convolutional method to model inverse cascade in forced two-dimensional turbulence

Contact Info

Product

Resources

About