Machine Learning for Climate Modeling: Parameterizing Sub-Grid Fluxes for the Ocean Surface Boundary Layer
Dr. Akash Sane, Princeton University, USA
Speaker |
Dr. Akash Sane, Princeton University, USA
|
---|---|
When |
Mar 11, 2025
from 10:00 AM to 11:00 AM |
Where | Via zoom |
Add event to calendar |
![]() ![]() |
SEMINAR TALK
Title: Machine Learning for Climate Modeling: Parameterizing Sub-Grid Fluxes for the Ocean Surface Boundary Layer
Abstract: The ocean surface boundary layer (OSBL) plays a crucial role in the ocean by modulating the exchange of mass and energy between the atmosphere and ocean interior via vertical turbulent mixing. The processes driving this mixing cannot be resolved in ocean climate models, necessitating the use of numerous ad hoc components for their parameterizations. These ad hoc components contribute to uncertainty in climate simulations. In this talk, I will describe improvements in an existing energetics based parameterization of vertical mixing for the OSBL in the NOAA-Geophysical Fluid Dynamics Laboratory’s ocean climate model. I will demonstrate how neural networks, trained to predict the eddy diffusivity profile from high-fidelity and expensive turbulence schemes, enhances the vertical mixing scheme in the climate model. These networks replace ad hoc components while maintaining the conservation principles of the standard ocean model equations. This is crucial for their effective use in climate simulations. The enhanced scheme outperforms its predecessor by reducing biases in the mixed-layer depth and modestly improving the tropical upper ocean stratification in ocean-only global simulations. Further, approximate equations that can replace the neural networks show similar improvements but with a lower computational cost and interpretability. This work is one of the first few demonstrations of successfully applying machine learning to target improvements in a sub-grid parameterization of turbulent mixing used in ocean climate models.
Title: Machine Learning for Climate Modeling: Parameterizing Sub-Grid Fluxes for the Ocean Surface Boundary Layer
Abstract: The ocean surface boundary layer (OSBL) plays a crucial role in the ocean by modulating the exchange of mass and energy between the atmosphere and ocean interior via vertical turbulent mixing. The processes driving this mixing cannot be resolved in ocean climate models, necessitating the use of numerous ad hoc components for their parameterizations. These ad hoc components contribute to uncertainty in climate simulations. In this talk, I will describe improvements in an existing energetics based parameterization of vertical mixing for the OSBL in the NOAA-Geophysical Fluid Dynamics Laboratory’s ocean climate model. I will demonstrate how neural networks, trained to predict the eddy diffusivity profile from high-fidelity and expensive turbulence schemes, enhances the vertical mixing scheme in the climate model. These networks replace ad hoc components while maintaining the conservation principles of the standard ocean model equations. This is crucial for their effective use in climate simulations. The enhanced scheme outperforms its predecessor by reducing biases in the mixed-layer depth and modestly improving the tropical upper ocean stratification in ocean-only global simulations. Further, approximate equations that can replace the neural networks show similar improvements but with a lower computational cost and interpretability. This work is one of the first few demonstrations of successfully applying machine learning to target improvements in a sub-grid parameterization of turbulent mixing used in ocean climate models.
Speaker's Bio: Aakash Sane is a Postdoctoral Research Associate at Princeton University, USA, affiliated with NOAA’s Geophysical Fluid Dynamics Laboratory. He earned his Ph.D. in Engineering (Physical Oceanography) from Brown University, USA, in 2021. His research focuses on ocean turbulence, climate change, coastal and global ocean dynamics, sub-grid turbulence parameterizations, machine learning, and fluid mechanics..

Join Zoom Meeting
https://zoom.us/j/92067863467?pwd=XwkF7y9fgnKCFewE6zKpJhFO7a5q59.1
Meeting ID: 920 6786 3467
Passcode: 726143