Display Accessibility Tools

Accessibility Tools

Grayscale

Highlight Links

Change Contrast

Increase Text Size

Increase Letter Spacing

Readability Bar

Dyslexia Friendly Font

Increase Cursor Size

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