Saved in:
Bibliographic Details
Main Authors: Wu, Jiarong, Perezhogin, Pavel, Gagne, David John, Reichl, Brandon, Subramanian, Aneesh C., Thompson, Elizabeth, Zanna, Laure
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.03990
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917229155581952
author Wu, Jiarong
Perezhogin, Pavel
Gagne, David John
Reichl, Brandon
Subramanian, Aneesh C.
Thompson, Elizabeth
Zanna, Laure
author_facet Wu, Jiarong
Perezhogin, Pavel
Gagne, David John
Reichl, Brandon
Subramanian, Aneesh C.
Thompson, Elizabeth
Zanna, Laure
contents Accurately quantifying air-sea fluxes is important for understanding air-sea interactions and improving coupled weather and climate systems. This study introduces a probabilistic framework to represent the highly variable nature of air-sea fluxes, which is missing in deterministic bulk algorithms. Assuming Gaussian distributions conditioned on the input variables, we use artificial neural networks and eddy-covariance measurement data to estimate the mean and variance by minimizing negative log-likelihood loss. The trained neural networks provide alternative mean flux estimates to existing bulk algorithms, and quantify the uncertainty around the mean estimates. Stochastic parameterization of air-sea turbulent fluxes can be constructed by sampling from the predicted distributions. Tests in a single-column forced upper-ocean model suggest that changes in flux algorithms influence sea surface temperature and mixed layer depth seasonally. The ensemble spread in stochastic runs is most pronounced during spring restratification.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03990
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data-Driven Probabilistic Air-Sea Flux Parameterization
Wu, Jiarong
Perezhogin, Pavel
Gagne, David John
Reichl, Brandon
Subramanian, Aneesh C.
Thompson, Elizabeth
Zanna, Laure
Atmospheric and Oceanic Physics
Machine Learning
Applications
Accurately quantifying air-sea fluxes is important for understanding air-sea interactions and improving coupled weather and climate systems. This study introduces a probabilistic framework to represent the highly variable nature of air-sea fluxes, which is missing in deterministic bulk algorithms. Assuming Gaussian distributions conditioned on the input variables, we use artificial neural networks and eddy-covariance measurement data to estimate the mean and variance by minimizing negative log-likelihood loss. The trained neural networks provide alternative mean flux estimates to existing bulk algorithms, and quantify the uncertainty around the mean estimates. Stochastic parameterization of air-sea turbulent fluxes can be constructed by sampling from the predicted distributions. Tests in a single-column forced upper-ocean model suggest that changes in flux algorithms influence sea surface temperature and mixed layer depth seasonally. The ensemble spread in stochastic runs is most pronounced during spring restratification.
title Data-Driven Probabilistic Air-Sea Flux Parameterization
topic Atmospheric and Oceanic Physics
Machine Learning
Applications
url https://arxiv.org/abs/2503.03990