← All research

Transit photometry & RV

Characterization of planetary candidates

Characterizing planetary candidates them from transit light curves and radial-velocity signals

When a planet passes in front of its host star, the resulting photometric dip — a transit light curve — encodes the planet's radius, orbital inclination, and the limb-darkening profile of the star. With enough precision, repeated transits also reveal atmospheric absorption signatures, orbital decay, and transit-timing variations caused by companion planets.

We develop ML-assisted pipelines for radial-velocity analysis and transit detrending that reduce sensitivity to stellar activity — the dominant noise source in exoplanet detection. Our 2026 paper introduced a vision-transformer model for radial-velocity analysis that improves planet recovery in low signal-to-noise regimes.

Machine Learning for Radial Velocity Analysis. I. Vision Transformers as a Robust Alternative for Detecting Planetary Candidates

Anoop Gavankar, Tanish Mittal, Joe Ninan, Shravan Hanasoge

The Astronomical Journal, 171, 33 (2026)

Team members

Collaborators

  • Google DeepMindInternational
  • Google DeepMindComputing

For all peer-reviewed publications across the group, see the full publications page.

All publications →