[Esip-machinelearning] Karthik Kashinath (NERSC/Lawrence Berkeley Lab) @ ESIP ML Cluster Telecon (3/19)

[Cindy Lin]

Dear Cluster/Committee Participants,


This is a gentle reminder that the next meeting
for ESIP's Machine Learning Cluster is happening *this Friday, March 19, 12
pm ET/9 am PT*.


For this week's cluster meeting, we are honored to have Karthik Kashinath
from Lawrence Berkeley Lab give a talk.


*Where:* https://global.gotomeeting.com/join/422305101
<https://www.google.com/url?q=https://global.gotomeeting.com/join/422305101&sa=D&source=calendar&ust=1610050207409000&usg=AOvVaw2CdSfSn-RgC-OCHvajpKgQ>


You can also dial in using your phone.

United States: +1 (571) 317-3122


Access Code: 422-305-101


*Title: *Physics-informed Machine learning for weather and climate science


*Abstract: *Machine learning (ML) provides novel and powerful ways of
accurately and efficiently recognizing complex patterns, emulating
nonlinear dynamics, and predicting the spatio-temporal evolution of weather
and climate processes. ML and DL have had some remarkable successes in
challenging problems in complex physical systems such as turbulent flows
and weather and climate systems.

However, off-the-shelf ML and DL models do not always obey the fundamental
governing laws of physical systems, nor do they generalize well to
scenarios on which they have not been trained. We discuss briefly
approaches to incorporating physics and domain knowledge into ML models
towards achieving greater physical consistency, reduced training time,
improved data efficiency, and better generalization. Finally, we synthesize
the lessons learned and identify scientific, diagnostic, computational, and
resource challenges for developing truly robust and reliable
physics-informed ML models for turbulence, weather, and climate processes.


*Bio: *Karthik Kashinath leads various climate informatics projects at the
Big Data Center @ NERSC (Lawrence Berkeley Lab). He received his Bachelors
from the Indian Institute of Technology, Madras, Masters from Stanford
University and PhD from the University of Cambridge, U. K. His background
is in engineering and applied physics. He has worked on various projects
spanning a wide range of disciplines from supersonic aircraft engines to
battery technologies to complex chaotic systems and turbulence. His current
research interests lie in physics-informed machine learning and novel data
analytics and pattern discovery methods for large complex systems such as
Earth’s climate. When he is not in front of the computer he runs up
mountains, swims in lakes, and cooks exotic global cuisines.


Meeting Agenda doc:
https://docs.google.com/document/d/1NrnKP3KUBwKYDyVTXrTVBYg_yH3FmYbzsEiSQ6De5Ro/edit?usp=sharing


Best,
-- 
*Cindy Lin*
phd candidate | school of information + STS
university of michigan, ann arbor
cindylin.org
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.esipfed.org/pipermail/esip-machinelearning/attachments/20210315/af7369e9/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Title-abstract-bio-KKashinath-ESIP.docx
Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
Size: 180171 bytes
Desc: not available
URL: <http://lists.esipfed.org/pipermail/esip-machinelearning/attachments/20210315/af7369e9/attachment-0001.docx>