AI Center Seminar - AI4Science Series - Dr. Tomasz Kacprzak
Event details
| Date | 12.06.2024 |
| Hour | 11:00 › 12:00 |
| Speaker | Dr. Tomasz Kacprzak |
| Location | Online |
| Category | Conferences - Seminars |
| Event Language | English |
Title
A big telescope and a big computer: how AI and HPC will enable next breakthroughs in our understanding of the Universe
Abstract
The upcoming mega-telescopes, such as European Space Agency’s recently launched Euclid satellite, and the upcoming radio Square Kilometer Array (SKA), will provide images of our universe over 10 billion years of cosmic history, and enable us to study its evolution with unprecedented level of detail. In the framework of simulations-based inference, the big telescopes deliver a throve of high-resolution observations and big computers provide the feature-rich numerical theory prediction. By using AI trained on simulations and performing inference on observations, we will be able us to differentiate between complex models of dark matter, dark energy, modified gravity, and astrophysics; a task unattainable by classical pen-and-paper analysis. This way, big computers paired with big telescopes will enable next breakthroughs in our understanding of the universe. In this talk, I will review the current and future applications of AI and HPC in cosmology in astrophysics, focusing on areas where they already play a “game changing" role. I will also present a number of yet-unsolved problems in data science, the solutions to which are critical for enabling next generation measurements in cosmology.
Bio
Tomasz Kacprzak is a Senior Data Scientist at the Swiss Data Science Center (Hub at the Paul Scherrer Institute) and at the ETH Zurich. He obtained his PhD in Physics and Astronomy from the University College London, as well as previously a MSc in Machine Learning from the same university. His focus is on interdisciplinary science in physics and artificial intelligence, in particular on applications of machine learning and high-performance computing to solve otherwise-untractable problems in physics and cosmology. On the cosmology side, he is involved in the Dark Energy Survey project, the Euclid satellite, and the Square Kilometer Array. More information: https://tomaszkacprzak.github.io/
A big telescope and a big computer: how AI and HPC will enable next breakthroughs in our understanding of the Universe
Abstract
The upcoming mega-telescopes, such as European Space Agency’s recently launched Euclid satellite, and the upcoming radio Square Kilometer Array (SKA), will provide images of our universe over 10 billion years of cosmic history, and enable us to study its evolution with unprecedented level of detail. In the framework of simulations-based inference, the big telescopes deliver a throve of high-resolution observations and big computers provide the feature-rich numerical theory prediction. By using AI trained on simulations and performing inference on observations, we will be able us to differentiate between complex models of dark matter, dark energy, modified gravity, and astrophysics; a task unattainable by classical pen-and-paper analysis. This way, big computers paired with big telescopes will enable next breakthroughs in our understanding of the universe. In this talk, I will review the current and future applications of AI and HPC in cosmology in astrophysics, focusing on areas where they already play a “game changing" role. I will also present a number of yet-unsolved problems in data science, the solutions to which are critical for enabling next generation measurements in cosmology.
Bio
Tomasz Kacprzak is a Senior Data Scientist at the Swiss Data Science Center (Hub at the Paul Scherrer Institute) and at the ETH Zurich. He obtained his PhD in Physics and Astronomy from the University College London, as well as previously a MSc in Machine Learning from the same university. His focus is on interdisciplinary science in physics and artificial intelligence, in particular on applications of machine learning and high-performance computing to solve otherwise-untractable problems in physics and cosmology. On the cosmology side, he is involved in the Dark Energy Survey project, the Euclid satellite, and the Square Kilometer Array. More information: https://tomaszkacprzak.github.io/
Practical information
- General public
- Free