Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy

Abstract

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 in astronomy through its three waves, from the early use of multilayer perceptrons, to the rise of convolutional and recurrent neural networks, and finally to the current era of unsupervised and generative deep learning methods. With the exponential growth of astronomical data, deep learning techniques offer an unprecedented opportunity to uncover valuable insights and tackle previously intractable problems. As we enter the anticipated fourth wave of astronomical connectionism, we argue for the adoption of GPT-like foundation models fine-tuned for astronomical applications. Such models could harness the wealth of high-quality, multimodal astronomical data to serve state-of-the-art downstream tasks. To keep pace with advancements driven by Big Tech, we propose a collaborative, open-source approach within the astronomy community to develop and maintain these foundation models, fostering a symbiotic relationship between AI and astronomy that capitalizes on the unique strengths of both fields.

arXiv comment75 pages, 327 references, 32 figures. Review accepted in Royal Society Open Science

References in corpus (87)

• The Sloan Digital Sky Survey: Technical Summary
• The Seventh Data Release of the Sloan Digital Sky Survey
• The Transiting Exoplanet Survey Satellite
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Deep Learning for Anomaly Detection: A Review
• Deep Visual Domain Adaptation: A Survey
• CANDELS: The Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey - The Hubble Space Telescope Observations, Imaging Data Products and Mosaics
• Overview of the DESI Legacy Imaging Surveys
• First results from the IllustrisTNG simulations: matter and galaxy clustering
• Overview of the SDSS-IV MaNGA Survey: Mapping Nearby Galaxies at Apache Point Observatory
• Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• LaMDA: Language Models for Dialog Applications
• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• COSMOS : Hubble Space Telescope Observations
• ANNz: estimating photometric redshifts using artificial neural networks
• Galaxy Zoo: Exploring the Motivations of Citizen Science Volunteers
• Data Mining and Machine Learning in Astronomy
• NVAE: A Deep Hierarchical Variational Autoencoder
• The FIRST Bright Quasar Survey. II. 60 Nights and 1200 Spectra Later
• Compute Trends Across Three Eras of Machine Learning
• Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Scaling Language Models: Methods, Analysis & Insights from Training Gopher
• Estimating photometric redshifts with artificial neural networks
• Large-scale dark matter simulations
• Results from the Supernova Photometric Classification Challenge
• Predicting Solar Flares Using a Long Short-Term Memory Network
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• Classifying Radio Galaxies with Convolutional Neural Network
• Searching for pulsars using image pattern recognition
• A recurrent neural network for classification of unevenly sampled variable stars
• Photometric redshifts with the Multilayer Perceptron Neural Network: application to the HDF-S and SDSS
• MassiveNuS: Cosmological Massive Neutrino Simulations
• AUTOMATED MORPHOLOGICAL CLASSIFICATION OF APM GALAXIES BY SUPERVISED ARTIFICIAL NEURAL NETWORKS
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Deep Recurrent Neural Networks for Supernovae Classification
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• Neural computation as a tool for galaxy classification : methods and examples
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Galaxies, Human Eyes and Artificial Neural Networks
• Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
• Fast cosmic web simulations with generative adversarial networks
• Fast cosmological parameter estimation using neural networks
• Self-Supervised Representation Learning for Astronomical Images
• A COMPARATIVE STUDY OF MORPHOLOGICAL CLASSIFICATIONS OF APM GALAXIES
• Physical Parameterization of Stellar Spectra: The Neural Network Approach
• Wide Field Imaging. I. Applications of Neural Networks to object detection and star/galaxy classification
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• A simple and robust method for automated photometric classification of supernovae using neural networks
• Neural Networks and Photometric Redshifts
• A sample of Seyfert-2 galaxies with ultra-luminous galaxy-wide NLRs -- Quasar light echos?
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• A multiscale approach to environment and its influence on the colour distribution of galaxies
• Deblending galaxy superpositions with branched generative adversarial networks
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Deblending galaxies with Variational Autoencoders: a joint multi-band, multi-instrument approach
• Deep Learning for Image Sequence Classification of Astronomical Events
• Realistic galaxy image simulation via score-based generative models
• Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
• Denoising Gravitational Waves using Deep Learning with Recurrent Denoising Autoencoders
• Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-Encoders
• Supervised detection of exoplanets in high-contrast imaging sequences
• Probabilistic Mass Mapping with Neural Score Estimation
• ASTROMER: A transformer-based embedding for the representation of light curves
• Euclid preparation: XIII. Forecasts for galaxy morphology with the Euclid Survey using Deep Generative Models
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• An autoencoder of stellar spectra and its application in automatically estimating atmospheric parameters
• The Intrinsic Scatter of the Radial Acceleration Relation
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light
• Classification of Fermi-LAT sources with deep learning using energy and time spectra
• Use of neural networks for the identification of new z>=3.6 QSOs from FIRST-SDSS DR5
• Realistic galaxy images and improved robustness in machine learning tasks from generative modelling
• Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks
• Foreground removal from CMB temperature maps using an MLP neural network
• Radio Galaxy Zoo EMU: Towards a Semantic Radio Galaxy Morphology Taxonomy
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• Pix2Prof: fast extraction of sequential information from galaxy imagery via a deep natural language 'captioning' model
• Artificial Neural Networks as Non-Linear Extensions of Statistical Methods in Astronomy
• Selection of quasar candidates from combined radio and optical surveys using neural networks
• An Explorative Approach for Inspecting Kepler Data

Cited by in corpus (20)

• Hydrodynamical simulations of the galaxy population: enduring successes and outstanding challenges
• A review of unsupervised learning in astronomy
• Towards an astronomical foundation model for stars with a Transformer-based model
• Empirical assessment of ChatGPT's answering capabilities in natural science and engineering
• Are Large Language Models a Threat to Digital Public Goods? Evidence from Activity on Stack Overflow
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Deriving the star formation histories of galaxies from spectra with simulation-based inference
• Learning the Universe: Cosmological and Astrophysical Parameter Inference with Galaxy Luminosity Functions and Colours
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Morpho-Photometric Classification of KiDS DR5 Sources Based on Neural Networks: A Comprehensive Star-Quasar-Galaxy Catalog
• Simulating images of radio galaxies with diffusion models
• Uncertainty estimation for time series classification: Exploring predictive uncertainty in transformer-based models for variable stars
• Neutron star envelopes with machine learning: a single-hidden-layer neural network application
• Exploring Galaxy Properties of eCALIFA with Contrastive Learning
• Datacube segmentation via Deep Spectral Clustering
• The Galaxy Activity, Torus, and Outflow Survey (GATOS): N. Unveiling physical processes in local active galaxies. Unsupervised hierarchical clustering of JWST MIRI/MRS observations
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• EMU/GAMA: A new approach to characterising radio luminosity functions