Scholar
Keiya Hirashima
Google Scholar ID: DHaJvdIAAAAJ
RIEKN Center for Interdisciplinary Theoretical and Mathematical Sciences
Citations & Impact
Citations
76
H-index
4
i10-index
2
Publications
11
Co-authors
5
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Published paper: ASURA-FDPS-ML: Star-by-star Galaxy Simulations Accelerated by Surrogate Modeling for Supernova Feedback, accepted for publication in ApJ
- Published paper: First High-Resolution Galaxy Simulations Accelerated by a 3D Surrogate Model for Supernovae, NeurIPS ML4PS Workshop
- Published paper: Surrogate Modeling for Computationally Expensive Simulations of Supernovae in High-Resolution Galaxy Simulations, NeurIPS 2023 AI for Science Workshop
- Published paper: 3D-Spatiotemporal Forecasting the Expansion of Supernova Shells Using Deep Learning toward High-Resolution Galaxy Simulations, MNRAS, 526, 3
- Published paper: Predicting the Expansion of Supernova Shells Using Deep Learning toward Highly Resolved Galaxy Simulations, Proceedings of the International Astronomical Union, 16(S362), 209-214
- Published paper: Predicting the expansion of supernova shell for high-resolution galaxy simulations using deep learning, J. Phys.: Conf. Ser. 2207 012050
- Award: The Next Generation Researcher Award, The 4th Research Workshop of Program for Promoting Research on the Supercomputer Fugaku, February 2025
- Grant: Grant-in-Aid for JSPS Fellows, Project ID 22J23077, 22KJ1153, FY2022 - FY2024, 2.5M JPY
Background
- RIKEN Special Postdoctoral Researcher working on the development of codes and algorithms for galaxy formation simulations. Mainly focuses on developing Communication Avoiding Algorithm (CA Algorithm) for large-scale computation using deep learning techniques in the field of computer vision.
Miscellany
- Gender: Male
- Address: 2-1, Hirosawa, Wako, Saitama 351-0198, Japan
- Email: keiya.hirashima[at]riken.jp
- Update: May 6th, 2025
