Session 2: Astrophysics and Astronomy
Aug 30, 2021 (updated Oct 5, 2021)
The growing size of modern astronomical surveys makes a reliable analysis using established image processing techniques difficult. AI based analysis promises to provide a viable solution to handing the ever increasing data volumes. Other areas of astronomy and astrophysics also benefit significantly from deep neural networks for classification purposes and to generate simulated data.
Monday, October 11, 2021 14:45 - 16:15 UTC (click for other timezones)
Panelists
- Francisco Forster - Adjunct Professor at Center for Mathematical Modeling Associate Researcher at Millennium Institute for Astrophysics
- Marco Cavaglià - Professor of Physics at the Missouri University of Science and Technology
- Ting-Yun Cheng - Postdoctoral Research Associate at Durham University
- Yuan-Sen Ting - Australian National University
Conveners
- Elena Cuoco, Head of the Data Science Office at the European Gravitational Observatory and Scuola Normale Superiore di Pisa
- Željko Ivezić, University of Washington
- Lukas Nellen, Universidad Nacional Autónoma de México (UNAM)
Contributions
- Yuan-Sen Ting: On Modelling Complex Systems in Astronomy
- Ting-Yun Cheng (Sunny): Beyond the Hbble Sequence: Exploring galaxy morphology with unsupervised machine learning
- Carlos Giovanni Martinez Gutierrez: Discovery of structures in galaxy images with MinHashing, k-means and SIFT
- Biprateep Dey: Interpretable Photometric Redshifts using Deep Capsule Networks
- Lior Shamir: Artificial intelligence challenges in analysis of large astronomical databases