Astronomy and AI – online event

As part of the 2024 STFC Astronomy and AI summer school, we are also running an online event aimed at a wider cohort of astronomy PhD students who have an interest in AI. This event will take place the week prior to the summer school, on Wednesday 3rd July, and feature panel discussions on broader questions about AI, alongside the release of a number of recorded case studies showcasing how AI is being utilised by astronomers today.

Schedule

09.15-10.15 Introduction
10.15-10.30 Break
10.30-12.00 Panel Discussion I
12.00-13.00 Lunch
13.00-13.45 TBD
13.45-14.00 Break
14.00-15.30 Panel Discussion II

Panel Discussions

[In progress] The following lists the speakers participating in the panel discussions for the online event. These discussions will tackle the broader questions of AI and its use in both astronomy and in a wider context.

Panel Discussion IPanel Discussion II
Ingo Waldmann (University College London)Mike Walmsley (University of Toronto)
Josh Wilde (The Open University)



Case Studies of AI in Astronomy

[In progress] A number of researchers and PhD students have kindly provided recorded talks of how they utilise AI in their own work. These case studies are listed below, including brief descriptions and a link to each recording. They cover a variety of research topics and types of AI, so are definitely worth a watch!

In addition to the individual case studies below, we will also release a shortened compilation video to provide an overview of the variety of AI uses in astronomical research.

NameAffiliationTitleDetails
Mike WalmsleyUniversity of TorontoComputer vision for galaxy imagesModern telescopes take far more images than humans could ever look through, and so we rely on automated methods to measure what galaxies look like. AI is an excellent tool for solving this visual recognition problem. I’ll talk about how AI models have changed over the last few years to learn efficiently and quickly adapt to new measurement tasks.
Josh WildeThe Open University
Ruby Pearce-CaseyThe Open UniversityUsing cGANs for Anomaly Detection: Hunting for Gravitational Lensing Systems in EuclidGravitational lensing is a powerful tool that directly probes all clustering components in the universe through their gravitational effect on light from distant background sources. The problem arises in finding gravitational lenses, and, with the accelerated growth in data volume and complexity in astronomy, machine-learning-aided lens searches have proven successful.

We present a proof of concept for an alternative method of strong gravitational lens finding using a conditional Generative Adversarial Network (cGAN). We use Early Release Observation (ERO) images of the Perseus Cluster from Euclid, covering 0.57 sq. degrees on the sky, and the network is based on the pix2pix architecture with an adapted U-Net generator. We train our model to predict Euclid’s NISP-H band flux (1.54-2.00µm) from a combination of the filters NISP-J, NISP-Y and VIS band (0.55-1.54µm) in 40,000 cut-outs from the Perseus Cluster which are 20×20 arcseconds in size. We test the cGAN on 5,000 cut-outs from the Perseus cluster, 10% of which contain a simulated strong gravitational lens painted into the cut-out based on a Singular Isothermal Ellipsoid model. Candidate gravitational lenses and cut-outs with a gravitational lens painted in were deliberated excluded from the model’s training data set such that gravitational lensing systems remain unknown to the network. We find that the cGAN can accurately predict the NISP-H band flux of the cut-outs from the Perseus cluster. However, the model fails to predict the NISP-H band flux of the cut-outs containing the simulated gravitational lenses, with a larger difference between the model’s prediction and ground truth for lenses with extended arcs and Einstein rings, suggesting that the cGAN can be used as an anomaly detector for an alternative method of lens finding.
Ingo WaldmannUniversity College LondonMachine learning in exoplanet characterisationThe upcoming decade promises remarkable progress in our grasp of exoplanet formation, evolution, and an in-depth assessment of their climates and possible habitability. With the James Webb Space Telescope now in orbit, we’re at the threshold of high-precision atmospheric studies of these distant worlds. This milestone, combined with forthcoming endeavours like the ELTs and the Ariel space mission, positions us in an era rich in high-precision exoplanetary data. In my talk’s initial segment, I’ll explore the use of simulation-based inference, deep surrogate models, and Explainable AI in refining time-series data and leveraging inverse modelling to extract exoplanet attributes from observations.

In the second part, I’ll delve into our machine-learning-centric data challenges. It’s noteworthy that many challenges in exoplanet data analysis resonate with issues keenly explored in the machine learning realm. Yet, interdisciplinary collaboration has often been stymied by language barriers and domain unfamiliarity. Addressing this, as part of the ESA Ariel Space mission, we have organised four machine learning challenges, hosted at prestigious AI conferences like NeurIPS and ECML, attracting hundreds of participating teams annually. I will discuss how such challenges can catalyse rapid, sturdy AI advancements in this budding domain and pave the way for more resilient AI solutions in the future.

Getting Started with AI in Astronomy

With the field of AI and deep learning ever expanding and evolving, it can be daunting at first to figure out where to start and difficult to understand what might be of use to you.

The GitHub repository below provides links and information about AI, covering general concepts, how artificial neural networks work, types of deep learning, tools and packages, and examples of how AI has been used in the field of astronomy. It is non-exhaustive but can hopefully act as an initial guide.

https://github.com/PlanetJames/AI-in-astronomy
– Repository created by Dr James Pearson (The Open University)