Newsお知らせ

    2023/10/27
    New published paper: Surrogate Modeling for Computationally Expensive Simulations of Supernovae in High-Resolution Galaxy SimulationsNEW
    2023/10/26
    Press Release: Deep learning speeds up galactic calculations --A new way to simulate supernovae may help shed light on our cosmic origins--
    2023/10/23
    Press Release: AIが描く超新星爆発の広がり ――深層学習を用いた超新星爆発シミュレーションの高速再現技術――
    2023/9/18
    New published paper: 3D-Spatiotemporal Forecasting the Expansion of Supernova Shells Using Deep Learning toward High-Resolution Galaxy SimulationsNEW

    About

    I am working on the development of codes and algorithms for galaxy formation simulations using massively parallel supercomputers. I am mainly developing Communication Avoiding Algorithm (CA Algorithm) for large-scale computation using deep learning techniques in the field of computer vision.

    Degrees

    B.E., Informatics and Mathematical Science, Engineering, Kyoto University, Japan, 2020

    M.S., Astronomy, Science, The University of Tokyo, Japan, 2022

    Education

    Mar. 2020 Undergraduate School of Informatics and Mathematical Science, Kyoto University, Japan

    Mar. 2022 Master's course, Department of Astronomy, Graduate School of Science, The University of Tokyo, Japan

    Apr. 2022 - (present) Ph.D. course, Department of Astronomy, Graduate School of Science, The University of Tokyo, Japan

    Publications

    [ First-Authoured, Refereed ]
  1. Hirashima, K., Moriwaki, K., Fujii, S. M., Hirai, Y., Saitoh, R. T., Makino, J, Steinwandel, P. U., Ho, S. (2024). First High-Resolution Galaxy Simulations Accelerated by a 3D Surrogate Model for Supernovae, NeurIPS ML4PS Workshop, [LINK]
  2. Hirashima, K., Moriwaki, K., Fujii, M., Hirai, Y., Saitoh, T., Makino, J, & Ho, S. (2023). Surrogate Modeling for Computationally Expensive Simulations of Supernovae in High-Resolution Galaxy Simulations, NeurIPS 2023 AI for Science Workshop, [OpenReview]
  3. Hirashima, K., Moriwaki, K., Fujii, M., Hirai, Y., Saitoh, T., & Makino, J. (2023). 3D-Spatiotemporal Forecasting the Expansion of Supernova Shells Using Deep Learning toward High-Resolution Galaxy Simulations, MNRAS, 526, 3, [ADS]
  4. Hirashima, K., Moriwaki, K., Fujii, M., Hirai, Y., Saitoh, T., & Makino, J. (2023). Predicting the Expansion of Supernova Shells Using Deep Learning toward Highly Resolved Galaxy Simulations. Proceedings of the International Astronomical Union, 16(S362), 209-214. doi:10.1017/S1743921322001739, [ADS]
  5. Hirashima, K., Moriwaki, K., Fujii, M. S., Hirai, Y., Saitoh, T., Makino, J. (2022). Predicting the expansion of supernova shell for high-resolution galaxy simulations using deep learning, J. Phys.: Conf. Ser. 2207 012050, [ADS]
  6. [ First-Authoured, Non-Refereed ]
  7. Hirashima, K., Moriwaki, K., Fujii, S. M., Hirai, Y., Saitoh, R. T., Makino, J, Steinwandel, P. U., Ho, S. (2024). ASURA-FDPS-ML: Star-by-star Galaxy Simulations Accelerated by Surrogate Modeling for Supernova Feedback, arXiv:2410.23346, submitted to ApJ, [ADS]
  8. [ Co-Authoured, Refereed ]
  9. Ohana, R., McCabe, M., et al. (incl. Hirashima, K.), (2024). The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning, NeurIPS 2024 Track Datasets and Benchmarks, [ADS]
  10. Ohana, R., McCabe, M., et al. (incl. Hirashima, K.), (2024). The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning, NeurIPS 2024 Workshop on Data-driven and Differentiable Simulations, [OpenReview]
  11. [ Co-Authoured, Non-Refereed ]
  12. Golkar, S., Bietti, A., Pettee, M. et al (incl. Hirashima, K.)., (2024). Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task, arXiv:2406.02585, [ADS]
  13. Grants, Fellowships, and Scholarships

    Research Grants
  14. Grant-in-Aid for JSPS Fellows, Forecasting SN shells using deep learning for video predictions toward higher-resolution galaxy simulations (22J23077, 22KJ1153), FY2022 - FY2024, (2.5M JPY)
  15. JSPS Overseas Challenge Program for Young Researchers (CCA/Flatiron Institute, USA), FY2022, (11,700)
  16. The University of Tokyo Computational Science Alliance Travel Support (For NeurIPS 2023 workshop), 2023
  17. International Astronomical Union Grants 2024 (for XXXII IAU General Assembly in Cape Town, South Africa)
  18. Fellowships
  19. Accepted for Special Postdoctoral Researcher of RIKEN, FY2025 - FY2027, (45,000/yr)
  20. Accepted for Overseas Research Fellowships of the Japan Society for the Promotion of Science for Young Scientists, FY2025 - FY2027, (50,000/yr)
  21. Accepted for Research Fellowships of the Japan Society for the Promotion of Science for Young Scientists PD, FY2025 - FY2027, (30,000/yr)
  22. Special allowance for research grant in the final year of JSPS fellow DC (特別研究員-DCの採用最終年次における研究奨励金特別手当), FY2024, (2,230)
  23. Research Fellowships of the Japan Society for the Promotion of Science for Young Scientists DC1, FY2022 - FY2024, (20,000/yr)
  24. The University of Tokyo Doctoral Fellowship for Creation of Intelligent World, WINGS-IIW (The University of Tokyo World Leading Innovative Graduate Study Program - Innovation for Intelligent World), FY2022 - FY 2024, (5,000/yr)
  25. Scholarships
  26. JEES-Mitsubishi Corporation Science Technology Student Scholarship, FY2022, (11,000/yr)
  27. Repayment Exemption for Students with Excellent Grades (Exemption of all of loan), Japan Student Services Organization (JASSO) Type I (Interest-free loan) scholarship, FY2021
  28. Japan Student Services Organization (JASSO) Type I (Interest-Free loan) scholarship, FY2020 - FY2021, (5,000/yr)
  29. Long-term Visiting

  30. Guest Researcher, Center for Computational Astrophysics, Flatiron Institute, Simons Foundation, NY, USA, (supported by Simons Foundation and JSPS), 13mos in 2023/2024.
  31. Invited Guest Researcher, Center for Astrophysics | Harvard-Smithsonian, MA, USA, (supported by JSPS and MIT), 2023/11.
  32. Research Intern, RIKEN R-CCS International HPC Computational Science Internship Program, Kobe, Japan, 2020/08.
  33. International Conferences

    [ Refereed ]
  34. Surrogate Modeling for Supernova Feedback toward Star-by-Star Simulations of Milky-Way-sized Galaxies, XXXII IAU General Assembly 2024, FM7 NEW HORIZONS AT THE INTERFACE BETWEEN COMPUTATIONAL ASTROPHYSICS AND BIG DATA, Cape Town, South Africa, 2024/08 [LINK]
  35. Surrogate Modeling for Computationally Expensive Simulations of Supernovae in High-Resolution Galaxy Simulations, NeurIPS 2023 AI for Science Workshop, New Orleans, USA, 2023/12 [LINK]
  36. [ Non-Refereed ]
  37. Surrogate Modeling for Supernova Feedback toward Star-by-Star Simulations of Milky-Way-sized Galaxies, The 2nd edition of the International Conference on Machine Learning for Astrophysics (ML4ASTRO2), Sicily, Italy, 2024/07 [LINK]
  38. Surrogate Modeling for Supernova Feedback toward High-Resolution Galaxy Simulations, AI-driven discovery in physics and astrophysics, Kavli IPMU, The University of Tokyo, Chiba, Japan, 2024/01 [LINK]
  39. Surrogate modeling for supernova feedback in galaxy simulations, The 8th Japan-US Science Forum in Boston, Consulate-General of Japan, Boston, USA, 2023/11 [LINK]
  40. Forecasting the expansion of SN shells toward high resolution galaxy simulations, Cosmic Connections: A ML X Astrophysics Symposium, poster, Flatiron Institute, NY, USA, 2023/05 [LINK]
  41. Forecasting the expansion of SN shells using deep learning toward high-resolution galaxy simulations, Challenges and Innovations in Computational Astrophysics IV, 10, Live Zoom, 2022/11 [LINK]
  42. Forecasting SN explosions Using Deep Learning toward High-Resolution Galaxy Simulations, IAUS 368: Machine Learning in Astronomy: Possibilities and Pitfalls, 3322, e-talk, 2022/8 [LINK]
  43. Predicting the expansion of supernova shell for high-resolution galaxy simulations using deep learning, IAUS 362: Predictive Power of Computational Astrophysics as a Discovery Tool, Live Zoom, 2021/11 [LINK]
  44. Predicting the expansion of supernova shell for high-resolution galaxy simulations using deep learning, XXXII IUPAP Conference on Computational Physics, Live Zoom, 2021/7 [LINK]
  45. Predicting the expansion of supernova shell for high-resolution galaxy simulations using deep learning, IAU CB1 ChaICA-III2021, Live Zoom, 2021/6 [LINK]
  46. Domestic Conferences

    [ Invited ]
  47. 超新星フィードバックのサロゲートモデルを用いた銀河形成シミュレーションの高速化 (Accelerating Galaxy Simulations using Surrogate Modeling for Supernova Feedback), The 2024 Spring Annual Meeting of the Astronomical Society of Japan, Z223r, Tokyo, 2024/3 [LINK]
  48. [ Contributed ]
  49. AIサロゲートモデルを用いたstar-by-star銀河形成シミュレーションの高速化 (Accelerating Star-by-star Galaxy Simulations using AI Surrogate Modeling), The 2024 Autumn Annual Meeting of the Astronomical Society of Japan, X14a, Hyogo, 2024/9 [LINK]
  50. Surrogate Modeling for Hydrodynamics and Fluid dynamics, Nuclear Fusion and its Interdisciplinary Fields, Tokyo, 2024/05 [LINK]
  51. Surrogate Modeling for Supernova Feedback toward Star-by-star Galaxy Simulations, 第3回「富岳」成果創出加速プログラム研究交流会, Poster, Tokyo, 2024/03 [LINK]
  52. 高解像度銀河形成シミュレーションに向けた超新星フィードバックのサロゲートモデリング, 「成果創出加速」基礎科学合同シンポジウム, Tokyo, 2023/12 [LINK]
  53. Star-by-star銀河形成シミュレーションに向けた超新星フィードバックのサロゲートモデリング (Surrogate Modeling for Supernovae Feedback in toward star-by-star Galaxy Simulations), The 2023 Autumn Annual Meeting of the Astronomical Society of Japan, X46a, 2023/09 [LINK]
  54. Accelerating SN simulations using deep learning toward star-by-star galaxy simulations, Astro AI with Fugaku workshop, Tokyo, 2023/09 [LINK]
  55. 超新星フィードバックのためのサロゲートモデルの開発, シミュレーション天文学のこれまでとこれから -ハードウェア・アプリケーション・サイエンス-, Kobe, 2023/09 [LINK]
  56. 機械学習を用いた高解像度銀河形成シミュレーションの高解像度化, 第2回 スーパーコンピュータ「富岳」成果創出加速プログラム 研究交流会, 2023/03, Online [LINK]
  57. 機械学習を用いた超新星爆発シェル膨張の予測, 「富岳で加速する素粒子・原子核・宇宙・惑星」シンポジウム, Kobe, 2022/12 [LINK]
  58. 深層学習による超新星シェル膨張予測を用いた高解像度銀河形成シミュレー ションの高速化 (Forecasting the expansion of Supernova shells toward accelerating high-resolution galaxy simulations), Data Science in Astronomy 2022, b03, The Institute of Statistical Mathematics, 2022/10 [LINK]
  59. Accelerating high-resolution galaxy simulations using deep learning for predicting the expansion of SN shells, The 2022 Autumn Annual Meeting of the Astronomical Society of Japan, X52a, Live Zoom, 2022/9 [LINK]
  60. Predicting the expansion of supernova shells using deep learning and computer vision toward high-resolution galaxy simulations, The 2022 Spring Annual Meeting of the Astronomical Society of Japan, X61a, Live Zoom, 2022/3 [LINK]
  61. 深層学習を用いた超新星爆発によるシェル膨張の予測, 天体形成研究会2021, 筑波大学, オンライン, 2021/10 [LINK]
  62. Predicting the Expansion of Supernova Shell Using Deep Learning, The 2021 Autumn Annual Meeting of the Astronomical Society of Japan, X44a, Live Zoom, 2021/9 [LINK]
  63. 深層学習を用いた超新星爆発によるシェル膨張の予測, 2021年度 第51回 天文・天体物理若手夏の学校, オンライン, 2021/8 [LINK]
  64. Predicting the expansion of supernova shell for high-resolution galaxy simulations using deep learning, 新学術A03班 夏の会合プログラム, 九州大学・オンライン, 2021/7
  65. 星団の高速・高精度シミュレーション用アルゴ リズムBRIDGEとその応用, 2020年度 第50回 天文・天体物理若手夏の学校, オンライン, 2020/8 [LINK]
  66. Seminars

  67. Galaxy Formation Seminar, Center for Computational Astrophysics / Flatiron Institute, 2024/09
  68. Surrogate Modeling for Supernova Feedback toward Star-by-Star Simulations of Milky-Way-sized Galaxies, ABBL-iTHEMS joint astro seminar, RIKEN Interdisciplinary Theoretical and Mathematical Sciences Program, 2024/05 [LINK]
  69. Douglas Finkbeiner's group meeting, Center for Astrophysics | Harvard University, 2023/11
  70. Astro-AI group meeting, Center for Astrophysics | Harvard University, 2023/11
  71. Sony Group Corporation, Online, 2023/11
  72. CPS Seminar, Center for Planetary Science, Kobe University, 2023/10
  73. Ken Nagamine's group meeting, Osaka University, 2023/10
  74. The University of Tokyo GCL/IIW Monthly meeting, online, 2023/9
  75. Evan Schneider's group meeting, University of Pittsburgh, 2023/6
  76. Coffee talk, Institute for Advanced Study, 2023/6
  77. Tri-state Cosmology X data Science tag up, Center for Computational Astrophysics / Flatiron Institute, 2023/4
  78. Teaching Experiences

  79. Galaxy School 2022 [LINK]
    • 2022, Teaching Assistant.
  80. Computational Astronomy
    • Summer 2021, Teaching Assistant for Assoc. Prof. Michiko Fujii.
    • Summer 2020, Teaching Assistant for Assoc. Prof. Michiko Fujii.

    Professional Services

  81. LOC, AI-driven discovery in physics and astrophysics, Kavli IPMU, The University of Tokyo, Chiba, Japan, 2024/01 [LINK]
  82. Main Organizer, The 53rd Summer School on Astronomy and Astrophysics, The University of Tokyo, Tokyo, Japan, 2023, [LINK]
  83. Other Experiences

  84. Jun. 2022, The 12th International HPC Summer School 2022, Greek. [LINK]
  85. 2021・2022, 筑紫丘高校難関大講座, 講師, 福岡県立筑紫丘高等学校.
  86. 2020・2021, 第1回・第2回全国高校AIアスリート選手権大会, 問題作成・講師.
  87. Dec. 2020, 理学部ガイダンス@駒場-なぜ私は理学を選んだか-, ジュニアスタッフ.
  88. Oct. 2020, 学問研究ワークショップ, 講師, 兵庫県立洲本高等学校.
  89. Aug. 2020, RIKEN R-CCS International HPC Computational Science Internship Program 2020, Intern, RIKEN R-CCS. [LINK]