Recurrent Localization Networks applied to the Lippmann-Schwinger Equation

Kelly, Conlain

Title:

Recurrent Localization Networks applied to the Lippmann-Schwinger Equation

dc.contributor.author	Kelly, Conlain
dc.contributor.corporatename	Georgia Institute of Technology. Center for Career Discovery and Development	en_US
dc.contributor.corporatename	Georgia Institute of Technology. Office of Graduate Studies	en_US
dc.contributor.corporatename	Georgia Institute of Technology. Office of the Vice Provost for Graduate Education and Faculty Development	en_US
dc.contributor.corporatename	Georgia Institute of Technology. Student Government Association	en_US
dc.contributor.corporatename	Georgia Institute of Technology. School of Computational Science and Engineering	en_US
dc.date.accessioned	2022-02-05T03:48:19Z
dc.date.available	2022-02-05T03:48:19Z
dc.date.issued	2022-01-27
dc.description	Presented at the Georgia Tech Career, Research, and Innovation Development Conference (CRIDC), January 27, 2022.	en_US
dc.description	The Career, Research, and Innovation Development Conference (CRIDC) is designed to equip on-campus and online graduate students with tools and knowledge to thrive in an ever-changing job market.	en_US
dc.description.abstract	The process of discovering and designing new materials is very costly, both in terms of time and human effort. One of the most expensive parts is experimentation — before a new material can be trusted, it must first be tested extensively to understand all of its properties. These experiments usually take the form of either physical (real-world) tests or computer simulations. Unfortunately, classical physics-based simulations are still quite slow. In the process of designing a new material, a great number (e.g. thousands, millions) of simulations must be conducted. This constitutes a major bottleneck for discovering new materials. This work explores different methods to accelerate materials discovery by replacing slow, physics-based simulations with faster, reduced-order models based on machine learning. Specifically, the original physical governing equation is converted into an equivalent form more amenable for learning called the Lippmann-Schwinger (L-S) form. A recurrent series of convolutional neural networks (CNNs) is then used to approximately solve the L-S equation. This hybrid architecture, called a recurrent localization network (RLN), leverages the strengths of machine learning while still permitting a physics-based interpretation. As a demonstration, an RLN is trained to solve for interior strain fields of an elastic microstructure, producing high-accuracy results a thousand times faster than a classical Finite-Element simulation. Additionally, this methodology is faster, more accurate, and more interpretable than purely-data-driven models for the same problem. Since a wide range of physical systems can be converted into an equivalent L-S form, this architecture has potential applications across numerous problems in materials science.	en_US
dc.description.sponsorship	NSF GRFP Grant No. DGE-2039655	en_US
dc.identifier.uri	http://hdl.handle.net/1853/66237
dc.language.iso	en_US	en_US
dc.publisher	Georgia Institute of Technology	en_US
dc.relation.ispartofseries	CRIDC
dc.subject	Computational materials science	en_US
dc.subject	Machine learning	en_US
dc.subject	Convolutional neural networks	en_US
dc.title	Recurrent Localization Networks applied to the Lippmann-Schwinger Equation	en_US
dc.type	Text
dc.type.genre	Poster
dspace.entity.type	Publication
local.contributor.corporatename	Office of Graduate Education
local.relation.ispartofseries	Career, Research, and Innovation Development Conference
relation.isOrgUnitOfPublication	d9390dfc-6e95-4e95-b14b-d1812f375040
relation.isSeriesOfPublication	4976ff66-25a7-4118-9c75-a356abde9732