Speaker
Estuti Shukla
(Penn State University)
Description
In the realm of general relativity, given two metric solutions in different gauges, determining whether they describe the same physical scenario poses significant challenges. This study proposes a novel application of machine learning techniques to address this issue within the context of numerical relativity. We introduce the first implementation of neural networks to learn the mapping between two metric solutions with identical manifold structure. We will also discuss potential application of how this approach can be used to compare various numerical relativity codes.
Author
Estuti Shukla
(Penn State University)
