Login

Physics in the AI era

24–27 Sept 2024
University of Pisa
Europe/Rome timezone

Contact

Session

Cosmology

25 Sept 2024, 09:00
Aula Azzurra (Scuola Normale Superiore)

Aula Azzurra

Scuola Normale Superiore

Presentation materials

There are no materials yet.

  1. 37. Cosmology from the first billion years as seen with the 21cm line
    Prof. Andrei Mesinger (Scuola Normale Superiore)
    25/09/2024, 09:00
  2. 38. Machine Learning for Astrophysics & Cosmology
    Dr Caroline Heneka (University of Heidelberg)
    25/09/2024, 09:40
  3. 39. Machine Learning of the Cosmic 21-cm Signal
    Dr David Prelogovic
    25/09/2024, 10:05
  4. 57. Generative models for large-scale structures
    Prof. Kana Moriwaki (University of Tokyo)
    25/09/2024, 11:20
  5. 28. Machine learning based inference of high redshift observations.
    Hovav Lazare (Ben Gurion University)
    25/09/2024, 11:45
    Poster + application for talk session

    High redshift observations, such as the 21cm signal, luminosity functions, etc., carries immense potential to probe the formation and properties of the first galaxies, and beyond $\Lambda \mathrm{CDM}$ Cosmology. However, a complete statistical analysis of such observation is limited by the time consuming nature of simulators. Using machine learning based emulators we can overcome this...

    Go to contribution page
  6. 31. Evaluating Summary Statistics with Mutual Information for Cosmological Inference
    Ce Sui
    25/09/2024, 12:00
    Poster + application for talk session

    The ability to compress observational data and accurately estimate physical parameters relies heavily on informative summary statistics. In this paper, we introduce the use of mutual information (MI) as a means of evaluating the quality of summary statistics in inference tasks. MI can assess the sufficiency of summaries, and provide a quantitative basis for comparison. We propose to estimate...

    Go to contribution page
  7. 44. Machine learning in astrophysics
    Prof. Tobias Buck (University of Heidelberg)
    25/09/2024, 14:30
  8. 50. Solving inverse problems with diffusion models
    Alexandre Adam (University of Montreal)
    25/09/2024, 15:10
  9. 51. Dusting off the Cosmic Microwave Background with Diffusion Models
    Dr Bruno Régaldo-Saint Blancard
    25/09/2024, 15:35
  10. 26. Analysing edge-on galaxies with deep learning
    Dr Žofia Chrobáková (Mullard Space Science Laboratory, University College London, Holmbury St Mary, Dorking, Surrey RH5 6NT, UK)
    25/09/2024, 16:30
    Poster + application for talk session

    The advent of large astronomical surveys, such as Euclid, will offer unprecedented insights into the statistical properties of galaxies. However, the large amounts of data that will be generated by these surveys call for the application of machine learning methods. For this purpose, we trained the YOLOv5 algorithm to accurately detect spiral, edge-on galaxies in astronomical images and the...

    Go to contribution page
  11. 25. Emulating the Interstellar Medium Chemistry with Neural Operators
    Dr Lorenzo Branca (Interdisziplinares Zentrum fur¨ Wissenschaftliches Rechnen, Universitat¨ Heidelberg)
    25/09/2024, 16:45
    Poster + application for talk session

    Understanding the interstellar medium (ISM) chemistry is pivotal for the study of galaxy formation and evolution. Traditional computational models rely on costly ordinary differential equation (ODE) solvers to simulate complex photo-chemical processes. This study introduces a novel approach using DeepONet neural operators to emulate a non-equilibrium chemical network, significantly reducing...

    Go to contribution page
  12. 7. Neural Network Approaches for Quasar and Galaxy Continuum Estimation: A Comparative Study of Autoencoder and U-Net Architectures
    Dr Francesco Pistis (Università degli studi Milano-Bicocca)
    25/09/2024, 17:00
    Poster + application for talk session

    The rise of new spectroscopic surveys, such as the WHT Enhanced Area Velocity Explorer (WEAVE), EUCLID, and the 4-metre Multi-Object Spectroscopic Telescope (4MOST), alongside the ongoing Dark Energy Spectroscopic Instrument (DESI), will significantly increase the volume of observed quasar and galaxy spectra. This surge necessitates the development of automated methods for accurate spectral...

    Go to contribution page
  13. 23. Estimation of Reionization Parameters from 21-cm Bispectrum using BNN-based Emulator
    Yashrajsinh Mahida (Indian Institute of Technology, Indore)
    Poster + application for talk session

    The upcoming large scale surveys like SKA, LOFAR and HERA will soon start probing the Universe in the era of Cosmic Dawn (CD) and Epoch of Reionization (EoR). To understand and interpret the observations from various experiments we need novel data analysis and interpretation techniques, which involve fast simulations of the expected signal, developing statistics for interpreting the signal and...

    Go to contribution page
Building timetable...