Detection, instance segmentation, and classification for astronomical surveys with deep learning (deepdisc): detectron2 implementation and demonstration with …

G Merz, Y Liu, CJ Burke, PD Aleo, X Liu… - Monthly Notices of …, 2023 - academic.oup.com
The next generation of wide-field deep astronomical surveys will deliver unprecedented
amounts of images through the 2020s and beyond. As both the sensitivity and depth of …

Galaxy light profile convolutional neural networks (GaLNets). I. Fast and accurate structural parameters for billion-galaxy samples

R Li, NR Napolitano, N Roy, C Tortora… - The Astrophysical …, 2022 - iopscience.iop.org
Next-generation large sky surveys will observe up to billions of galaxies for which basic
structural parameters are needed to study their evolution. This is a challenging task that, for …

Reduction of supernova light curves by vector Gaussian processes

MV Kornilov, TA Semenikhin… - Monthly Notices of the …, 2023 - academic.oup.com
Bolometric light curves play an important role in understanding the underlying physics of
various astrophysical phenomena, as they allow for a comprehensive modelling of the event …

Light curve completion and forecasting using fast and scalable Gaussian processes (MuyGPs)

IR Goumiri, AM Dunton, AL Muyskens… - arxiv preprint arxiv …, 2022 - arxiv.org
Temporal variations of apparent magnitude, called light curves, are observational statistics
of interest captured by telescopes over long periods of time. Light curves afford the …

Parameter measurement based on photometric images-I. The method and the gas-phase metallicity of spiral galaxies

JH Cai, N Li, HF Yang, LL Wang, AY Zheng… - Astronomy & …, 2025 - aanda.org
The gas-phase metallicity is a crucial parameter for understanding the evolution of galaxies.
Considering that the number of multiband galaxy images can typically reach tens of millions …

Stellar parameter prediction and spectral simulation using machine learning-A systematic comparison of methods with HARPS observational data

V Cvrček, M Romaniello, R Šára, W Freudling… - Astronomy & …, 2025 - aanda.org
Aims. We applied machine learning to the entire data history of ESO's High Accuracy Radial
Velocity Planet Searcher (HARPS) instrument. Our primary goal was to recover the physical …

Deep Sky Objects Detection with Deep Learning for Electronically Assisted Astronomy

O Parisot, M Jaziri - Astronomy, 2024 - mdpi.com
Electronically Assisted Astronomy is a fascinating activity requiring suitable conditions and
expertise to be fully appreciated. Complex equipment, light pollution around urban areas …

A robust approach to Gaussian process implementation

J Mukangango, A Muyskens… - Advances in Statistical …, 2024 - ascmo.copernicus.org
Gaussian process (GP) regression is a flexible modeling technique used to predict outputs
and to capture uncertainty in the predictions. However, the GP regression process becomes …

Exploration with Scalable Gaussian Process Reinforcement Learning

CJ Miller, BC Soper, A Muyskens, BW Priest… - 2024 - osti.gov
Exploration is a challenging problem in reinforcement learning (RL), especially in
environments with sparse rewards. Quantifying and utilizing the parametric uncertainty has …

Closely-Spaced Object Classification Using MuyGPyS

K Pruett, N McNaughton, M Schneider - arxiv preprint arxiv:2311.10904, 2023 - arxiv.org
Accurately detecting rendezvous and proximity operations (RPO) is crucial for
understanding how objects are behaving in the space domain. However, detecting closely …