[Eoas-seminar] MET Seminar - Thursday February 9 - Dr. Zachary Labe (NOAA GFDL/Princeton University)

[eoas-seminar at lists.fsu.edu]

Dear all,

Please join us this Thursday February 9 for a Meteorology seminar, given by Dr. Zachary Labe<https://zacklabe.com> of NOAA GFDL/Princeton University. Dr. Labe will speak about "Exploring explainable machine learning for detecting changes in climate” (abstract below).

Dr. Labe will be joining us virtually but we will gather in EOA 1044 to participate in the seminar. If you cannot attend in person due to a medical reason or approved work out of town, please contact Allison Wing (awing at fsu.edu<mailto:awing at fsu.edu>) for remote access. Otherwise, we look forward to seeing everyone in 1044! Please join us for refreshments prior to the beginning of the talk at 3:15 PM.

If you are interested in meeting with the speaker, please contact Allison Wing.

DATE: Thursday February 9
SEMINAR TIME: Refreshments at 3 PM, Talk 3:15 PM - 4:15 PM.
SEMINAR LOCATION: EOA 1044 (speaker remote)
SPEAKER: Dr. Zachary Labe<https://zacklabe.com>

TITLE: Exploring explainable machine learning for detecting changes in climate

ABSTRACT: The popularity of deep learning methods, such as neural networks, continues to rapidly grow. The interest in these tools also coincides with a growing influx of big data, high performance computing capabilities, and the need for greater efficiency in solving a range of tasks. Specifically, in climate science, we often consider detection and attribution problems to help disentangle external climate forcing from internal variability. In this seminar, I will show examples of how relatively simple classification problems can be combined with explainable artificial intelligence methods to improve our understanding of historical and future climate projections. To make their predictions, we find that the neural networks are often leveraging regional patterns of forced signals within climate model large ensembles and observations. These same explainability frameworks can be easily adapted for a wide variety of applications in the Earth sciences. However, there is also some hesitancy for considering the use of neural networks due to concerns about their reliability, reproducibility, and interpretability.

We look forward to seeing you there!

Cheers,

Allison

——————————————————
Allison Wing, Ph.D.
Associate Professor
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/20230206/8a205315/attachment.html>