Velocity Data With Deep Learning Toward Earth
Researchers have developed a new deep-learning framework to improve the detection of Earth-mass planets in radial-velocity data. By using physically motivated spectral representations, the model successfully retrieves planetary signals despite the interference of stellar activity.
Why it matters
This advancement provides a more statistically rigorous method for identifying exoplanets, potentially accelerating the discovery of Earth-like worlds.
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 article is a technical summary of scientific research with no political or social agenda.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in