18–22 Jan 2027
International Conference Hall, Academia Sinica
Asia/Taipei timezone

From Arrival Directions to Candidate Sources: A Graph Neural Network Approach to UHECRs

Not scheduled
20m
Lecture Hall (International Conference Hall, Academia Sinica)

Lecture Hall

International Conference Hall, Academia Sinica

Academia Sinica Humanities and Social Sciences Building, No. 128號, Section 2, Academia Rd, Nangang District, Taipei City, 115 115臺北市南港區研究院路二段128號中央研究院人文社會科學館

Speaker

Oleg Kalashev (Institute for Nuclear Research RAS)

Description

We present a graph convolutional neural network (GCN) approach to analyzing the arrival directions of ultra-high-energy cosmic rays (UHECRs). By exploiting the sensitivity of GCNs to local spatial structure, the method enables the detection of small- and intermediate-scale anisotropies in UHECR arrival-direction distributions. Taking a set of active galactic nuclei (AGNs) as candidate sources, the model identifies patterns in UHECR sky maps and associates them with individual sources. We demonstrate the method by estimating the contributions of several nearby AGNs to the cosmic-ray flux observed by the Pierre Auger Observatory. We also identify individual events most likely to be associated with each candidate source, offering new opportunities to investigate cosmic-ray production and propagation in AGN environments.

Author

Oleg Kalashev (Institute for Nuclear Research RAS)

Co-author

Iuliia Moroz (Institute for Nuclear Research RAS)

Presentation materials

There are no materials yet.