DELOS: Detecting Shallow Transits in Kepler Photometry Using a Contrastive-Learning Framework
arXiv:2605.29428v1 Announce Type: cross Abstract: We present DEtection in phase-folded Light curves with cOntrastive Scoring (DELOS), a contrastive-learning-based framework designed to search for shallow transits in Kepler photometry. DELOS combines GPU-accelerated phase folding, optimized phase binning, and a custom one-dimensional convolutional encoder to assign a transit-likeness score to each folded light curve, thereby producing a score periodogram over trial periods without relying on pre-detected threshold-crossing events. Focusing on intermediate-to-long-period signals with orbital per
The continuous advancements in AI and machine learning techniques, particularly contrastive learning, are being applied to scientific discovery processes that generate large datasets.
This development allows for more efficient and robust detection of subtle astronomical phenomena, potentially leading to new exoplanet discoveries and a deeper understanding of planetary systems.
The reliance on pre-detected threshold-crossing events for transit detection is reduced, enabling the discovery of shallower, previously unidentifiable transits.
- · Astronomers
- · AI/ML researchers
- · Space agencies
- · GPU manufacturers
- · Traditional transit detection algorithms
- · Researchers relying on manual data analysis
More exoplanets, especially smaller and longer-period ones, will be identified from existing and future photometric data.
Increased availability of exoplanet data will refine planetary formation models and improve target selection for next-generation telescopes.
A higher number of detected exoplanets could increase the statistical probability of finding Earth-like worlds, fueling astrobiology research.
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.AI