Parallel sessions

The use of Machine Learning (ML) techniques is currently greatly growing in astronomy. In this session, we bring together scientists who have successfully deployed ML algorithms in research with those who seek to take the first steps toward introducing these new algorithms into their research. Invited speakers will discuss the theory and applicability of ML algorithms in astrophysics, cosmology, and solar and atmospheric physics, and review the recent use of these techniques in astronomy. The remainder of the session will be dedicated to contributed talks showcasing research combining ML techniques with investigative scientific reasoning and deduction.

Schedule:

Session 1
13:00 Tanmoy Laskar, Eliot Ayache, Benjamin Giblin (Welcome)
13:05 Thomas Killestein “Bayesian convolutional neural networks for source classification: sifting the GOTO candidate stream”
13:20 Ingo Waldmann “The Ariel Space Mission Machine Learning Challenges”
13:35 Asa Bluck “Unraveling the nature of star formation quenching with machine learning”
13:50 Jacqueline den Hartogh “Classification algorithms for stellar abundances with dilution”
14:00 David Kinson “Machine learning identification of stellar populations in the Local Group irregular galaxy NGC 6822”
14:10 Matthew Mould “Neural network emulation of black hole merger distributions for gravitational wave population inference”
14:20 Poster Flashes (please ask to share your audio and video; the organizers will invite you up in the following order): 
1. Andrew Williamson, MLA07, “Lightning-Fast Gravitational-Wave Parameter Inference Through Neural Amortization”
2. Ilin Lazar, MLA06, “Galaxy Morphological Classification via Unsupervised Machine Learning: a Way Forward in the Exascale Era of Big Data Surveys”
3. Mirko Curti, MLA21, “What drives the scatter in the BPT diagrams? A Machine Learning based analysis”
4. Matthew Scourfield, MLA03, “Maximum information retrieval from DESI spectra”
5. Elena Garcia Broock, MLA04, “Performance of solar far-side active regions neural detection”
6. Samuel Spencer, MLA05, “Deep Learning Analysis of Imaging Atmospheric Cherenkov Telescope Data”

Session 2
16:00 Joanna Piotrowska “Extracting physical insight from a random forest classifier: A rigorous test of AGN feedback models against the observed local universe”
16:15 Micah Bowles “Paying Attention to Astronomy Data”
16:30 Kai Hou Yip: “Peeking inside the Black Box: Interpreting Deep Learning Models for Exoplanet Atmospheric Retrievals"
16:45 Peter Hatfield “Unknown Unknowns: Hybrid machine learning and template based photometric redshifts”
16:55 Rob McGibbon “Multi-Epoch Machine Learning”
17:05 Marc Huertas-Company “Summary & discussion”