Rochester Institute of Technology
Smarter Simulation Placement of Kilonova Light Curve Models for Computationally Inexpensive Surrogate Model Creation
Abstract
dc:description.abstractThe first detected binary neutron star merger GW170817 allowed for the simultaneous detection of gravitational and electromagnetic waves which started the era of multi-messenger astrophysics. The existence of an electromagnetic counterpart to a compact object merger allowed for a significantly deeper analysis of the merger event and much tighter resultant constraints on existing physical models of neutron stars, nuclear physics, and the Universe itself. Multi-messenger analysis requires sophisticated source modeling. For the foreseeable future, demanding computational resource costs will result in a sparse availability of state-of-the-art neutron star merger light curve simulations. Astrophysical inference can proceed using an alternate approach of creating computationally cheaper surrogate models based on the aforementioned state-of-the-art simulations. The work presented here focuses on the creation and interpolation of a library of light curve simulations suitable for the generation of surrogate models capable of conveying useful astrophysical information. It addresses the necessity of switching from grid-based simulation placement to an error-maximization approach which identifies the least understood regions of parameter space. Interpolation is introduced as the connecting factor between the long-term goal of surrogate model creation and the new simulation placement mechanism. Finally, a discussion about the iterative process of simulation placement using interpolation outputs describes how each new simulation brings the library one step closer to serving as a surrogate model training set.
Degree
thesis:*- Name thesis:degree_name
- Astrophysical Sciences and Technology (MS)
- Level thesis:degree_level
- Thesis
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ristic, Marko
- Contributors dc:contributor
-
- Richard O'Shaughnessy
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/10548