Harvesting spectroscopic and time series data with machine learning and artificial intelligence

www.wallpaperup.com + Badvviser/Getty Images/iStockphoto + news.unair.ac.id
Start Date
End Date

One dimensional data are commonplace in astronomy; spectroscopic data contain abundant physical and chemical information about the target being studied, while time series data are crucial for event detection and characterisation. It has now become critical to efficiently harvest the information contained in one dimensional data given the exponential growth of astronomical datasets in current large-scale surveys and future facilities such as JWST, Euclid, Rubin Observatory LSST, 4MOST, DESI, and WEAVE. It is therefore of great importance to increase the community’s attention and capability to cope with the plethora of upcoming one dimensional data.

As a tool, machine learning (ML) can improve both the quantity (how many we can analyse) and quality (how much we can harvest) of spectroscopic and time series datasets. With the growth of interests in ML algorithms applied to a variety of analyses of one dimensional data, we aim to bring together researchers in the community to share their research and insight.


Contributed talks are anticipated to be 10-15 minutes including time for questions. Contributions by research students and early career researchers are strongly encouraged.

Abstract submission (by Monday 5th December 2022): https://forms.gle/e2FWuRLGPrris2eH6

Confirmed overview speakers:

Emille Ishida, Research Engineer, French National Centre for Scientific Research

Emille Ishida is a Research Engineer at the French National Centre for Scientific Research and is based at the Laboratoire de Physique de Clermont Ferrand, France. She is an expert in the development of recommendation systems for astronomical data. Emille is the founder and manager of three interdisciplinary and international research networks (the Cosmostatistics Initiative - COIN, the SNAD collaboration and the Fink broker), where she conducts experiments related to machine learning applications to astronomy as well as investigates the role of astronomy as a trigger for innovation in academia.  Her research interests include adaptive machine learning, optimum experiment design, science of team science and studies on the future of the academic research environment.


Yuan-Sen Ting, Associate Professor, Australian National University

Yuan-Sen is an Associate Professor at ANU, jointly affiliated with the astronomy and computer science departments. Yuan-Sen's research applies machine learning to advance statistical inferences using large astronomical survey data. He grew up in Malaysia and received his PhD in astronomy and astrophysics from Harvard University in 2017. After graduating, Yuan Sen was awarded a joint postdoctoral fellowship from Princeton University, Carnegie Institute for Sciences, NASA Hubble and the Institute for Advanced Study at Princeton before moving to Australia. He also serves as the co-chair of the NASA Cosmic Programs Stars Science Interest Group and leads multiple future spectroscopic surveys as the science group leader. He is an author of more than 150 journal articles, many of them on topics at the frontier of astrophysics and machine learning.


10:30 – 11:00: Overview Talk

11:00 – 12:20: Contributed talks

12:30 – 13:30: Lunch

13:30 – 14:00: Invited Talk

14:00 – 15:20: Contributed talks

15:20 – 15:30: Discussion and Summary



Ting-Yun Cheng (Durham)

Ryan Cooke (Durham)

Annagrazia Puglisi (Durham)