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 HPC and AI in cosmology in astrophysics, focusing on areas where they already play an indispensable 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

Tomasz Kacprzak is a Senior Scientist at ETH Zurich and a Senior Data Scientist at the Swiss Data Science Center at the Paul Scherrer Institute. 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-intractable 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 at tomaszkacprzak.github.io.