TransitNet recovers 93% of injected Earth-size and sub-Earth transits at low SNR where BLS and TLS recover only 60%, while running 4-25 times faster.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
astro-ph.EP 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An ensemble of machine learning models trained jointly on Kepler and TESS data provides instrument-agnostic prioritization of exoplanet candidates.
citing papers explorer
-
TransitNet: A Compact Attention-Augmented Deep Learning Framework for Low-SNR Transit Blind Searches
TransitNet recovers 93% of injected Earth-size and sub-Earth transits at low SNR where BLS and TLS recover only 60%, while running 4-25 times faster.
-
Towards Instrument-Agnostic Exoplanet Candidate Prioritization
An ensemble of machine learning models trained jointly on Kepler and TESS data provides instrument-agnostic prioritization of exoplanet candidates.