AD – Thanks to Skillshare for sponsoring this video! The first 500 people to use my link will get a 1-month free trial of Skillshare: https://skl.sh/drbecky07241 | AI or artificial intelligence feels like a buzzword that you just can't escape these days. It's everywhere. And astrophysics is no exception, with the number of published research papers that either use or mention AI tools like machine learning and deep learning steadily increasing. So in this video, let's talk about what AI actually is – what it can do, what it can't do, because there's a lot of misinformation out there, before we then talk about 4 ways we astrophysicists use AI: i) classifying data, ii) finding weird things (anomaly detection), iii) inferring data, and iv) emulating simulations. This is by no means an exhaustive list. I'm sure many of my colleagues are using AI for research in other ways as well, not to mention using well-known tools like GitHub's Copilot to help them write code, or chatGPT to provide inspiration when trying to summarize research papers or grant proposals in abstracts. AI may have changed the way we work as astrophysicists, but astrophysics itself hasn't yet. The key word here, however, is *yet*, because given the pace at which AI is evolving, who knows what the next decade might bring!

Classify the shapes of galaxies in images from the brand new Euclid telescope to train an AI deep learning algorithm – https://galaxyzoo.org/

Watch Katie Bouman's TED talk explaining how the Event Horizon Telescope team created the black hole image: https://www.youtube.com/watch?v=BIvezCVcsYs

Smith & Geach (2023) – https://arxiv.org/pdf/2211.03796
Kembhavi & Pattnaik (2022) – https://link.springer.com/article/10.1007/s12036-022-09871-2
Fotopoulou (2024) – https://arxiv.org/pdf/2406.17316
Huppenkothen et al. (2023) – https://arxiv.org/pdf/2310.12528
Walmsley et al. (2020) – https://arxiv.org/pdf/1905.07424
Walmsley et al. (2023) – https://joss.theoj.org/papers/10.21105/joss.05312
Bowles et al. (2021) – https://arxiv.org/pdf/2012.01248
Huertas Company et al. (2023) – https://arxiv.org/pdf/2305.02478
Robertson et al. (2023) – https://arxiv.org/pdf/2208.11456
Yu et al. (2019) – https://arxiv.org/pdf/1904.02726
Osborn et al. (2020) – https://arxiv.org/pdf/1902.08544
Muthukrishna et al. (2019) – https://arxiv.org/pdf/1902.08544
Sooknunan et al. (2021) – https://arxiv.org/pdf/1811.08446
Cheng et al. (2021) – https://arxiv.org/pdf/2009.11932
Tohill et al. (2024) – https://arxiv.org/pdf/2306.17225
Muthukrishna et al. (2022) – https://arxiv.org/pdf/2111.00036
Perez-Carrasco et al. (2023) – https://iopscience.iop.org/article/10.3847/1538-3881/ace0c1
Mohale & Lochner (2024) – https://arxiv.org/pdf/2311.14157
Angeloudi et al. (2024) – https://arxiv.org/pdf/2407.00166
Rose et al. (2024) – https://arxiv.org/pdf/2405.00766
Conceição et al. (2024) – https://arxiv.org/pdf/2304.06099

00:00 – Introduction
01:33 – What is AI? Machine Learning vs. Deep Learning
05:46 – Advertisement – Skillshare
07:17 – (i) Classification of data
11:21 – (ii) Anomaly detection
13:29 – (iii) Conclusion from data
15:07 – (iv) Emulation of simulations
17:40 – The influence of AI on astrophysics
19:19 – Breakdowns

Video recorded with a Sony ⍺7 IV

—

My new book, /"A Brief History of Black Holes/

Please take the opportunity to connect with your friends and family and share this video with them if you find it useful.