Deep Learning for Line Intensity Mapping Observations: Information Extraction from Noisy Maps

Kana Moriwaki, Masato Shirasaki, Naoki Yoshida

The Astrophysical Journal Letters 2021 article cited by 18

Source Open-access PDF More in Physics & Astronomy

importance 6/10 ai assisted Galaxies: Formation, Evolution, Phenomena astronomy stage: research

Problem

Line intensity mapping observations are contaminated by foreground/background sources and noise, hindering study of large-scale structure and galaxy evolution.

Why it matters

LIM is a promising way to probe the large-scale structure of the universe.

What the AI did

Conditional GANs trained on 30,000 mock observation maps (Gaussian noise matched to NASA's SPHEREx expectations) extract H-alpha emission signals from noisy intensity maps.

Results

Peaks above 3.5-sigma noise located with 60% precision; one-point PDF and power spectrum accurately recovered

Impact

Demonstrated on mock data only; no real observational deployment stated.

Record

Venue	The Astrophysical Journal Letters
Published	2021
Work type	article
Authors	Kana Moriwaki, Masato Shirasaki, Naoki Yoshida
Citations	18 (OpenAlex, at import time)
References	14
Model or method	conditional generative adversarial networks (cGANs)
Organization	not stated in source
Primary source	https://doi.org/10.3847/2041-8213/abd17f
Open access	hybrid
Keywords	line intensity mapping, cGAN, SPHEREx, signal extraction, astrophysics, noise

Importance rating

6 / 10

significant — thousands to millions affected

LIM probes large-scale structure of the universe and galaxy evolution, a foundational science goal; foreground/noise removal is a key enabling capability, but abstract gives no scale figures.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Physics & Astronomy

#	Paper	Year	Citations	Importance
1	Magnetic control of tokamak plasmas through deep reinforcement learning Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan...	2022	739	7
2	Solving the quantum many-body problem with artificial neural networks Giuseppe Carleo, Matthias Troyer	2017	2,205	7
3	Learning high-accuracy error decoding for quantum processors Johannes Bausch, Andrew Senior, Francisco J. H. Heras, Thomas Edlich,...	2024	90	7
4	Optimizing Quantum Error Correction Codes with Reinforcement Learning Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Brie...	2019	158	7
5	Machine-learning-assisted correction of correlated qubit errors in a topological code Paul Baireuther, Thomas E. O’Brien, Brian Tarasinski, C. W. J. Beenakk...	2018	141	7