VIewing Space ThroUgh machine Learning and Astrostatistics (VISTULA)

Europe/Warsaw
207, second floor (NCBJ (Pasteura 7, Warsaw))

207, second floor

NCBJ (Pasteura 7, Warsaw)

ul. L. Pasteura 7 02-093 Warszawa Poland
Description

The workshop is organized as part of the project CLEVER: Cosmology & GaLaxy EVolution In The New ObsErving ProgRammes. Project founded by the Strategic Partnership project BPI/PST/2024/1/00019 by NAWA – Polish National Agency For Academic Exchange.

The rationale

Machine learning and modern statistical methods are becoming central tools in astrophysics and cosmology, from survey data reduction and photometric redshifts to time‑domain discovery, image classification and parameter inference. This workshop offers a structured introduction to statistical foundations and machine learning concepts.

The goal of this workshop is to provide a structured, beginner‑friendly entry point to machine learning and advanced statistics in astrophysics, while progressively reaching more advanced topics. The format will combine morning lectures with afternoon hands‑on sessions in which participants work through concrete astrophysical use cases under the guidance of the invited speakers and local tutors. 

The workshop is aimed at Master’s students, early‑stage PhD students and junior researchers from NCBJ, the University of Warsaw, and the CLEVER partner institutions. It will explicitly welcome participants with limited prior exposure to machine learning, provided they are comfortable with basic programming (e.g. Python) and standard statistical concepts. By the end of the workshop, participants should be able to: understand the main families of machine learning methods used in current astrophysical research; critically assess when a machine‑learning approach is appropriate; implement and evaluate simple models on real data; and recognise common pitfalls such as overfitting, data leakage and biased training sets.

The invited speakers span a broad range of applications including galaxy formation and evolution, large‑scale surveys, time‑domain and transient astronomy, exoplanets, radio morphology and cosmology.

Hosted in Warsaw as part of the CLEVER-NAWA partnership, the workshop will strengthen training and collaboration across the network by bringing together students, junior researchers, and invited experts for a hands-on introduction to machine learning and advanced statistics in astrophysics.

Invited speakers: 

  • Ting-Yun Cheng (Kapteyn Astronomical Institute in Groningen)
  • Antonio La Marca (Leiden Observatory)
  • Alex Razim (Centre for Astrophysics and Cosmology, Nova Gorica)
  • Carlo Schimd (Laboratoire d’Astrophysique de Marseille)
  • Will Pearson (National Centre for Nuclear Research)
SOC: LOC:
Paweł Bielewicz (chair)
Subhrata Dey
Miguel Figueira
Nandini Hazra
Mariana Jaber
Katarzyna Małek
Will Pearson
Antonio Vanzanella

Paweł Bielewicz (chair)
Nicola Principi Cavaterra
Aidan Cotter
Subhrata Dey
Orest Dorosh
Unnikrishnan Sureshkumar
Antonio Vanzanella

 

 

Registration
Registration
Participants
  • Nandini Hazra
  • Paweł Bielewicz
    • 10:00 11:30
      Probability and Statistics: a primer 1h 30m

      This lecture will cover the following topics:

      • probability space, random variables and random vectors, probability distributions, expectation values, variance and covariance.

      • Poisson noise, Gaussian noise, multiplicative noise: examples from electronic signals, electromagnetic spectra, images. Maximum likelihood estimators. Noise suppression and features detection: equalisation; linear and non-linear operations; filtering, smoothing, sharpening; Savitzky-Golay filter, bilateral filter, median filter, sigma-clipping.

      • Classification: Principal component analysis (PCA), kernel PCA, dimensional reduction.

      Speaker: Carlo Schimd (LAM)
    • 12:00 13:30
      Probability and Statistics: a primer 1h 30m
      Speaker: Carlo Schimd (LAM)
    • 14:30 16:00
      Stochastic processes and spectral analysis 1h 30m
      Speaker: Carlo Schimd (LAM)
    • 16:30 18:00
      Stochastic processes and spectral analysis 1h 30m
      Speaker: Carlo Schimd (LAM)
    • 10:00 11:30
      Introduction to Machine Learning 1h 30m
      Speaker: Alex Rezim (CAC, Nova Gorica)
    • 12:00 13:30
      Introduction to Machine Learning 1h 30m
      Speaker: Alex Rezim (CAC, Nova Gorica)
    • 14:30 16:00
      Introduction to Machine Learning 1h 30m
      Speaker: Alex Rezim (CAC, Nova Gorica)
    • 16:30 18:00
      Introduction to Machine Learning; hands-on session 1h 30m
      Speaker: Alex Rezim (CAC, Nova Gorica)
    • 10:00 11:30
      Supervised / unsupervised Machine Learning 1h 30m
      Speaker: Will or Antonio
    • 12:00 13:30
      Supervised / unsupervised Machine Learning 1h 30m
      Speaker: Will or Antonio
    • 14:30 16:00
      Supervised / unsupervised Machine Learning; hands-on session 1h 30m
      Speaker: Will or Antonio
    • 16:30 18:00
      Supervised / unsupervised Machine Learning; hands-on session 1h 30m
      Speaker: Will or Antonio
    • 10:00 11:30
      Supervised / unsupervised Machine Learning 1h 30m
      Speaker: Will or Antonio
    • 12:00 13:30
      Supervised / unsupervised Machine Learning 1h 30m
      Speaker: Will or Antonio
    • 14:30 16:00
      Supervised / unsupervised Machine Learning; hands-on session 1h 30m
      Speaker: Will or Antonio
    • 16:30 18:00
      Supervised / unsupervised Machine Learning; hands-on session 1h 30m
      Speaker: Will or Antonio
    • 10:00 11:30
      Regression 1h 30m
      Speaker: Ting-Yun (Sunny) Cheng (Kapteyn Astronomical Institute)
    • 12:00 13:30
      Regression 1h 30m
      Speaker: Ting-Yun (Sunny) Cheng (Kapteyn Astronomical Institute)
    • 14:30 16:00
      Regression; hands-on session 1h 30m
      Speaker: Ting-Yun (Sunny) Cheng (Kapteyn Astronomical Institute)
    • 16:30 18:00
      Regression; hands-on session 1h 30m
      Speaker: Ting-Yun (Sunny) Cheng (Kapteyn Astronomical Institute)
Your browser is out of date!

Update your browser to view this website correctly. Update my browser now

×