Comprehensive Exam of CMSE Vicente Amado
Department of Computational Mathematics, Science & Engineering
Michigan State University
Comprehensive Exam Notice
April 19th, 2024 – 2:00 PM -- STEM Rm 1001
Zoom link: 258 670 0887
Passcode: 896461
Leveraging Machine Learning to Revolutionize Astrophysics Research Processes: From Peer Review to Research Management
Vicente Amado Olivo
Abstract:
Our global research community is experiencing unprecedented exponential growth. Our
traditional research practices, however, were not designed to scale accordingly. Recent
technological advancements have the ability to facilitate the scientific process.
Computational meta-research leverages algorithmic techniques, such as machine learning,
to improve research processes from peer review to research management. In this comprehensive
examination, I focus on the astrophysics example of identifying the needs of the community
through the accurate tracking of telescope resources. The astrophysics community describes
the current use of resources (e.g. HST and JWST) in natural language scientific publications.
I present, our machine learning framework, employing natural language processing and
text classification techniques, to identify facility usage information from the large
corpus of scientific literature. The framework successfully classifies usage of facilities
with an accuracy of 92.9\%, evaluated against a labeled dataset compiled in collaboration
with the Space Telescope Science Institute. Additionally, I propose my dissertation
research, where I will develop a comprehensive registry of all active global researchers
employing machine learning to facilitate collaboration, minimize isolated research,
and accelerate scientific advancement. In conclusion, the machine learning methods
I present and propose exemplify how computational meta-research is enhancing the research
cycle, from optimizing resource allocation to augmenting research management.
Committee:
Wolfgang Kerzendorf (Chair)
Michael Murrillo
Parisa Kordjamshidi
Lou Strolger
Mario Malički