Bulletin of the American Physical Society
APS March Meeting 2022
Volume 67, Number 3
Monday–Friday, March 14–18, 2022; Chicago
Session M09: Predicting Nonlinear and Complex Systems with Machine Learning I
8:00 AM–11:00 AM,
Wednesday, March 16, 2022
Room: McCormick Place W-180
Sponsoring
Units:
GSNP DSOFT DCOMP
Chair: Ying-Cheng Lai, Arizona State University
Abstract: M09.00001 : A framework for seismic risk policy design and the assessment of avalanche-like event prediction in knitted fabric.*
8:00 AM–8:12 AM
Presenter:
Adèle Douin
(CNRS)
Authors:
Adèle Douin
(CNRS)
Frédéric Lechenault
(CNRS)
Jean-Phillipe Bruneton
(LIED)
Knitted fabric exhibits avalanche-like events when deformed, and as in most analogous seismic models, the occurrence of those time-intermittent and scale-invariant events cannot be accurately predicted, due to their peculiar statistics. We apply time-series prediction with Neural Networks on the mechanical response of the fabric in order to forecast future quantities. Furthermore, we discuss the assessment of such predictors, not only with standard metrics like the learning accuracy but also with more advanced ones taking into account the increase of risk with the amplitude. We present a framework allowing for the design of decision-making policies, as both a predictor evaluator and a provider of a clear strategy when dealing with risks, with KnitCity: a model seismically active city.
*Our research was found and supported by PRAIRIE (PaRis Artificial Intelligence Research InstitutE)
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2024 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700