1 code implementation • 13 Sep 2023 • Michael J. Smith, Luke Fleming, James E. Geach
EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifically with EO use-cases in mind.
no code implementations • 7 Nov 2022 • Michael J. Smith, James E. Geach
In this review, we explore the historical development and future prospects of artificial intelligence (AI) and deep learning in astronomy.
2 code implementations • 2 Nov 2021 • Michael J. Smith, James E. Geach, Ryan A. Jackson, Nikhil Arora, Connor Stone, Stéphane Courteau
We show that a Denoising Diffusion Probabalistic Model (DDPM), a class of score-based generative model, can be used to produce realistic mock images that mimic observations of galaxies.
Ranked #1 on Galaxy emergent property recreation on SDSS Galaxies
1 code implementation • 1 Feb 2021 • Kushatha Ntwaetsile, James E. Geach
We demonstrate the use of Haralick features for the automated classification of radio galaxies.
Instrumentation and Methods for Astrophysics Astrophysics of Galaxies
1 code implementation • 1 Oct 2020 • Michael J. Smith, Nikhil Arora, Connor Stone, Stéphane Courteau, James E. Geach
In perspective, Pix2Prof would take under an hour to infer profiles for $10^5$ galaxies on a single NVIDIA DGX-2 system.
1 code implementation • Submitted to MNRAS 2019 • Michael J. Smith, James E. Geach
Generative Adversarial Networks (GANs) are a class of artificial neural network that can produce realistic, but artificial, images that resemble those in a training set.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies
1 code implementation • 18 Sep 2017 • Alex Hocking, James E. Geach, Yi Sun, Neil Davey
We then apply the technique to the HST CANDELS fields, creating a catalogue of approximately 60, 000 classifications.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies
no code implementations • 30 Sep 2011 • James E. Geach
With a training set of ~3800 galaxies with z_spec<1, we achieve photometric redshift accuracies competitive with other (mainly template fitting) techniques that use a similar number of photometric bands (sigma(Dz)=0. 03 with a ~2% outlier rate when using u*-band to 8um photometry).
Instrumentation and Methods for Astrophysics