Large Scale Structure Cosmology with Artificial Intelligence

BIDS Machine Learning and Science Forum

ML&Sci Forum

April 18, 2022
11:00am to 12:00pm
Virtual Participation

BIDS Machine Learning and Science Forum
Date: Monday, April 18, 2022
Time: 11:00 AM - 12:00 PM Pacific Time
Location: Participate remotely using this Zoom link 

Large Scale Structure Cosmology with Artificial Intelligence

Speaker: Tomasz Kacprzak, ETH Zürich
Abstract: In large scale structure cosmology, the information about the cosmological parameters governing the evolution of the universe is contained in the complex and rich structure of dark matter density field. To date, this information was probed using simple human-designed statistics, which are not guaranteed, or even expected, to extract the full information content of the data. Recently we proposed an alternative analysis with deep learning that automatically designs the relevant features in order to maximise the information gain from the maps. In our results we observe a significant information gain for the deep analysis as compared to the power spectrum: I will present our latest results on the KiDS-1000 dataset as well as a forecast for combined probes analysis with AI, which we call DeepLSS. I will discuss the sources of the information gain from AI and describe the insights we can learn from it.

The BIDS Machine Learning and Science Forum meets biweekly to discuss current applications across a wide variety of research domains in the physical sciences and beyond. Hosted by BIDS Affiliates Uroš Seljak (professor of Physics at UC Berkeley) and Ben Nachman (physicist at Lawrence Berkeley National Laboratory), these active sessions bring together domain scientists, statisticians, and computer scientists who are either developing state-of-the-art methods or are interested in applying these methods in their research.  To receive email notifications about upcoming meetings, or to request more information, please contact the organizers at berkeleymlforum@gmail.comAll interested members of the UC Berkeley and Berkeley Lab communities are welcome and encouraged to attend. 


Tomasz Kacprzak

Eidgenössische Technische Hochschule (ETH) Zürich