[Eoas-seminar] MET Seminar - TODAY - Prof. Sara Shamekh (NYU)

[eoas-seminar at lists.fsu.edu]

Dear all,

This is a reminder of today's MET seminar, given by Prof Sara Shamekh on Toward a better representation of atmospheric processes using machine learning.

Snacks at 3, talk at 3:15 - see you in 1044! Email Allison Wing before 2:30 if you need the Zoom link.

Cheers,

Allison

Get Outlook for iOS<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Faka.ms%2Fo0ukef&data=05%7C02%7Ceoas-seminar%40lists.fsu.edu%7C8280a996a3ad4ffb84d808dc5a2be284%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C638484391720049995%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=4wmYovwwoYJihEo%2FnHMg6p%2BO4Iu2EvwPzuxyIBUs508%3D&reserved=0>
________________________________
From: Eoas-seminar <eoas-seminar-bounces at lists.fsu.edu> on behalf of eoas-seminar--- via Eoas-seminar <eoas-seminar at lists.fsu.edu>
Sent: Friday, April 5, 2024 9:01 AM
To: eoas-seminar--- via Eoas-seminar <eoas-seminar at lists.fsu.edu>
Cc: info at coaps.fsu.edu <info at coaps.fsu.edu>
Subject: [Eoas-seminar] MET Seminar - Thursday April 11 - Prof. Sara Shamekh (NYU)

Dear all,

Please join us next Thursday April 11 for a Meteorology seminar given by Prof. Sara Shamekh<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fsshamekh.com%2Fhome%2F&data=05%7C02%7Ceoas-seminar%40lists.fsu.edu%7C8280a996a3ad4ffb84d808dc5a2be284%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C638484391723800140%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=uwrGjWWshNTeATE5gq5Ih6Ry9MXHYo%2FnGdmovtgPp%2F4%3D&reserved=0> from NYU. she will speak about “Toward a better representation of atmospheric processes using machine learning”  (abstract below)

Prof. Shamekh will be joining us virtually, but we will still gather together in EOA 1044. If you have a medical excuse or other approved work off-campus, please contact Allison Wing (awing at fsu.edu<mailto:awing at fsu.edu>) for the Zoom link. Otherwise we look forward to seeing everyone in 1044.

Prof. Shamekh is also available for individual Zoom meetings on Thursday after the seminar. If you’d like to meet with her, please contact Allison Wing.

DATE: Thursday April 11
SEMINAR TIME: Refreshments at 3 PM, Talk 3:15 - 4:15 PM
SEMINAR LOCATION: EOA 1044 (Speaker remote)
SPEAKER: Prof. Sara Shamekh<https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fsshamekh.com%2Fhome%2F&data=05%7C02%7Ceoas-seminar%40lists.fsu.edu%7C8280a996a3ad4ffb84d808dc5a2be284%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C638484391723800140%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=uwrGjWWshNTeATE5gq5Ih6Ry9MXHYo%2FnGdmovtgPp%2F4%3D&reserved=0>

TITLE: Toward a better representation of atmospheric processes using machine learning

ABSTRACT: As the impact of climate change poses an urgent concern for the future of our planet and all its inhabitants, it's crucial that we accurately understand and model this complex system. By doing so, we can develop the ability to take action towards adapting to the impact of climate change. Climate models are important tools for understanding and predicting global and regional climate change, yet they exhibit key uncertainties that limit their applicability to future projections. Uncertainties in climate models partly originate from a poor or lacking representation of physical processes too small to be resolved by models, such as atmospheric boundary layer turbulence or clouds. Machine learning has the ability to capture nonlinear structures and relationships within complex data and, when combined with traditional physical models, can lead to a better representation of physical processes and provide new insights into atmospheric processes. In this talk, I will discuss few examples that highlight the potential of machine learning (ML) combined with physics and the new discoveries made possible through this framework. The first example uses reduced-order models to accurately represent vertical turbulent fluxes in the atmospheric boundary layer across turbulent regimes. The architecture of this model, in which I enforce a physical constraint, allows clear interpretability and discovery of the main modes of turbulent transport. I then compare this model with an ML-enhanced eddy-diffusivity-mass-flux parameterization (a typical conventional parameterization of atmospheric boundary layer) to demonstrate how machine-discovered modes of variability may differ from the conventional ones. I then discuss how to incorporate the spatial pattern of a field into a parameterization in order to address some of their limiting assumptions. These examples show the promise of ML in advancing our understanding and modeling of physical processes in the earth system. Despite these successes, many challenges remain to be addressed and many questions to be answered, making the future of this interdisciplinary area exciting.

We look forward to seeing you there!

Cheers,

Allison

--------------------------------------------
Allison A. Wing, Ph.D.
Werner A. and Shirley B. Baum Professor
Associate Professor, Department of Earth, Ocean, and Atmospheric Science
Florida State University
awing at fsu.edu

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.fsu.edu/pipermail/eoas-seminar/attachments/20240411/68a54191/attachment.html>