72 citations · 209 across the 11 of their papers we have counts for
11 papers
The Platonic Universe: Do Foundation Models See the Same Sky?
UniverseTBD, :, Trinidad Borrell +11
We investigate when foundation models converge towards shared representations, and how this convergence depends on model capacity, training regime, and model architecture. We take…
Dargana: fine-tuning EarthPT for dynamic tree canopy mapping from space
Michael J. Smith, Luke Fleming, James E. Geach +3
We present Dargana, a fine-tuned variant of the EarthPT time-series foundation model that achieves specialisation using <3% of its pre-training data volume and 5% of its pre-traini…
Towards more efficient agricultural practices via transformer-based crop type classification
E. Ulises Moya-Sánchez, Yazid S. Mikail, Daisy Nyang'anyi +2
Machine learning has great potential to increase crop production and resilience to climate change. Accurate maps of where crops are grown are a key input to a number of downstream…
Detangling the role of climate in vegetation productivity with an explainable convolutional neural network
Ricardo Barros Lourenço, Michael J. Smith, Sylvia Smullin +3
Forests of the Earth are a vital carbon sink while providing an essential habitat for biodiversity. Vegetation productivity (VP) is a critical indicator of carbon uptake in the atm…
EarthPT: a time series foundation model for Earth Observation
Michael J. Smith, Luke Fleming, James E. Geach
We introduce EarthPT -- an Earth Observation (EO) pretrained transformer. EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self…
Uncertainty estimation in Deep Learning for Panoptic segmentation
Michael Smith, Frank Ferrie
As deep learning-based computer vision algorithms continue to advance the state of the art, their robustness to real-world data continues to be an issue, making it difficult to bri…
Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
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. We trace the evolution of connectionism i…
Realistic galaxy image simulation via score-based generative models
Michael J. Smith, James E. Geach, Ryan A. Jackson +3
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 gala…
Pix2Prof: fast extraction of sequential information from galaxy imagery via a deep natural language 'captioning' model
Michael J. Smith, Nikhil Arora, Connor Stone +2
We present 'Pix2Prof', a deep learning model that can eliminate any manual steps taken when extracting galaxy profiles. We argue that a galaxy profile of any sort is conceptually s…
AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
Ashley Spindler, James E. Geach, Michael J. Smith
We present AstroVaDEr, a variational autoencoder designed to perform unsupervised clustering and synthetic image generation using astronomical imaging catalogues. The model is a co…
Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
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. In typical…