Modeling Doppler Shifts in Radial-Velocity Data with Deep Learning toward Earth-mass Exoplanet Detection
arXiv:2606.18464v1 Announce Type: cross Abstract: Detecting the tiny Doppler shifts induced by Earth-mass planets in stellar radial-velocity measurements remains extremely challenging due to stellar activity. Many deep-learning methods performing well on simulated data remain difficult to apply reliably on real stellar spectra. The aim of this work is to develop a deep-learning framework that generalizes to real, unseen spectra and improves the detectability of Earth-mass planets in radial-velocity data. We train artificial neural networks on HARPS-N solar spectra with injected planetary signa
Advances in deep learning and computational power are enabling more sophisticated analyses of complex astronomical data. The ongoing search for exoplanets, particularly Earth-mass ones, continues to drive innovation in detection methods.
This work represents a significant step towards reliably detecting Earth-mass exoplanets, which is crucial for understanding planetary formation and the potential for life beyond Earth. It addresses a major challenge in exoplanet research by developing AI robust enough for real-world astronomical data.
The ability to accurately model and filter stellar activity noise in radial-velocity data using deep learning will significantly improve the sensitivity and reliability of exoplanet detection efforts. This will accelerate the discovery of small, potentially habitable planets.
- · Astronomers and astrophysicists
- · Space agencies
- · AI/ML researchers in scientific domains
- · Deep learning framework developers
- · Traditional statistical modeling approaches for RV data
Improved detection rates of Earth-mass exoplanets through advanced AI-driven data analysis.
Accelerated understanding of exoplanetary demographics and the statistical likelihood of habitable worlds.
Enhanced public and scientific interest in astrobiology and potential for extraterrestrial life, driving further research and funding.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG