Conference: EPSCoR Workshop on Machine Learning for Analysis of High-Energy Cosmic Particles

University Of Delaware, Newark DE

Investigators

Abstract

This project will support a workshop on the application of Machine Learning for the Analysis of High-Energy Cosmic Particles. The workshop will be hosted by the University of Delaware and will bridge the themes: "Windows of the Universe" and "Harnessing the Data Revolution." Natural objects in the Universe, which are yet unknown, accelerate particles to energies far beyond human technological capabilities. A primary objective of particle astrophysics is to locate and comprehend the sources of these cosmic particles. To achieve this, specialized astroparticle observatories have been deployed to collect a diverse range of data. The advancement of science in this field hinges significantly on the quality of data analysis, benefiting from recent progress in machine learning, including artificial neural networks. Beyond the exchange of recent results and ideas in machine learning for high-energy particle astrophysics, the workshop will enhance scientific capabilities in this domain and serve the purpose of training a future workforce proficient in applying machine learning techniques. Special attention will be given to equity, diversity, and inclusion, with a hybrid format enabling broad participation, including both in-person and remote attendees. To maximize its impact, the workshop will involve co-organizers and participants from several EPSCoR states. The organizers will host a hybrid workshop with a conference-like format focusing on the application of machine learning for analyzing cosmic particles, including cosmic rays, high-energy gamma rays, and ultra-high-energy neutrinos—integral components of multi-messenger astronomy. Institutions in EPSCoR jurisdictions have begun to engage in this endeavor and anticipate a significant future role in NSF experiments, such as IceCube at the South Pole. Recognizing the value of in-person meetings for effective discussions and networking, this hybrid workshop will bring approximately 50 in-person participants to the University of Delaware for one week in early 2025, while also facilitating participation from additional online attendees. The organization of the workshop builds upon the successful multi-institutional collaboration established through the "NSF IceCube EPSCoR Initiative: IceCube and the Data Revolution" and will further encourage the involvement of EPSCoR institutions in this research area. Intellectual merits will be delivered through scientific exchanges during the workshop and, in the long term, by publishing workshop products on an open access platform in a citable manner. Supporting the NSF EPSCoR mission in various ways, the workshop will generate broader impacts and spur research initiatives by facilitating the exchange of scientific knowledge and fostering new connections among participants. By offering support to students from EPSCoR jurisdictions and underrepresented groups in STEM, the workshop will contribute to equality, diversity, and inclusion while preparing the next generation of the STEM workforce. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.