aiqbench analysis
This research applies Denoising AutoEncoders to clean JWST exoplanet transmission spectra, effectively removing stellar noise while maintaining high accuracy at a fraction of the computational cost of traditional methods. By leveraging unsupervised deep learning, the study offers an efficient pipeline for atmospheric retrieval that could become standard practice for analyzing rocky and sub-Neptune worlds.
Efficient reduction of stellar contamination and noise in planetary transmission spectra using neural networks
arXiv:2602.10330v4 Announce Type: replace-cross Abstract: The characterization of exoplanetary atmospheres has been transformed by the James Webb Space Telescope (JWST), whose infrared sensitivity enables transmission spectroscopy at unprecedented precision. However, stellar heterogeneities (e.g., spots and faculae) remain a dominant source of contamination that can bias atmospheric retrievals if not properly corrected. We present a methodology for reducing stellar contamination and instrument-specific noise from exoplanet transmission spectra using neural networks, in particular the so-called Denoising AutoEncoders (DAEs). Our goals are to enable fast, accurate corrections that improve the reliability of atmospheric parameter retrievals and to promote the use of unsupervised algorithms for efficient data processing. We designed and trained DAE architectures using large synthetic datasets of terrestrial (TRAPPIST-1e analogues) and sub-Neptune (K2-18b analogues) planets. Atmospheric retrieval experiments were then performed on contaminated spectra in order to compare our deep-learning approach against standard correction methods in terms of accuracy and computational cost. Our autoencoders successfully reconstruct uncontaminated spectra, preserving essential molecular features even in low-S/N regimes. In retrieval tests, the denoising autoencoder pre-processing yields atmospheric parameter estimates broadly comparable to those obtained with simultaneous stellar-contamination fitting. Notably, our method maintains a much lower computational cost, approximately one order of magnitude smaller. These results demonstrate that DAEs outperform conventional correction methods in computational efficiency while maintaining high accuracy, paving the way for their integration into future atmospheric characterization pipelines for both rocky and sub-Neptune exoplanets.
Abstract:The characterization of exoplanetary atmospheres has been transformed by the James Webb Space Telescope (JWST), whose infrared sensitivity enables transmission spectroscopy at unprecedented precision. However, stellar heterogeneities (e.g., spots and faculae) remain a dominant source of contamination that can bias atmospheric retrievals if not properly corrected. We present a methodology for reducing stellar contamination and instrument-specific noise from exoplanet transmission spectra using neural networks, in particular the so-called Denoising AutoEncoders (DAEs). Our goals are to enable fast, accurate corrections that improve the reliability of atmospheric parameter retrievals and to promote the use of unsupervised algorithms for efficient data processing. We designed and trained DAE architectures using large synthetic datasets of terrestrial (TRAPPIST-1e analogues) and sub-Neptune (K2-18b analogues) planets. Atmospheric retrieval experiments were then performed on contaminated spectra in order to compare our deep-learning approach against standard correction methods in terms of accuracy and computational cost. Our autoencoders successfully reconstruct uncontaminated spectra, preserving essential molecular features even in low-S/N regimes. In retrieval tests, the denoising autoencoder pre-processing yields atmospheric parameter estimates broadly comparable to those obtained with simultaneous stellar-contamination fitting. Notably, our method maintains a much lower computational cost, approximately one order of magnitude smaller. These results demonstrate that DAEs outperform conventional correction methods in computational efficiency while maintaining high accuracy, paving the way for their integration into future atmospheric characterization pipelines for both rocky and sub-Neptune exoplanets.
17 pages, 12 figures, 3 tables. Submitted to Astronomy & Astrophysics
Earth and Planetary Astrophysics (astro-ph.EP); Instrumentation and Methods for Astrophysics (astro-ph.IM); Machine Learning (cs.LG)
arXiv:2602.10330 [astro-ph.EP]
(or arXiv:2602.10330v4 [astro-ph.EP] for this version)
From: David S. Duque-Castaño [view email] [v1] Tue, 10 Feb 2026 22:07:18 UTC (7,569 KB) [v2] Thu, 12 Feb 2026 02:25:40 UTC (7,419 KB) [v3] Tue, 23 Jun 2026 16:51:01 UTC (3,518 KB) [v4] Mon, 31 Aug 2026 05:40:23 UTC (1,923 KB)
Full text under the publisher's open licence · 302 words
Related coverage
Operational Range Bounding in Spectroscopy: A Safety Cage Framework for Machine Learning Models
arXiv · Sep 15, 2026
Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT
METR · Jul 21, 2026
A quantum frequency converter cuts noise to 35 counts per second
Quantum Zeitgeist · Oct 14, 2026
Quantum graphs use interference to boost data transfer
Quantum Zeitgeist · Oct 1, 2026