AI model EXOVEIL detects exoplanets from stellar behavior

Researchers have developed EXOVEIL, a novel system for detecting exoplanets using a Transformer-based world model trained on Kepler light curves. This system learns a star's normal behavior and identifies deviations indicative of transits, even for single-transit events. EXOVEIL demonstrates strong performance on existing datasets and shows promising zero-shot transfer capabilities to new missions like TESS, approaching the detection limits for Earth-analog planets. AI

IMPACT This AI-driven approach could significantly enhance exoplanet discovery rates and improve the detection of Earth-like planets.

RANK_REASON The cluster describes a new AI model and methodology published in an academic paper for exoplanet detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• EXOVEIL
• Kepler
• PLATO
• TESS
• Transformer
• XGBoost

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →