ExoVeil: How a Single Transit Shadow Reveals Exoplanets ✛ ✦
Context
Classical transit-detection algorithms require knowing the period and a phase-folded signal. If a planet crosses the disk just once over the whole observation — typical for long-period Earth twins — these methods fail. That’s exactly where the PLATO mission and future habitability research focus. ExoVeil flips the paradigm: instead of classifying known signals, the system learns to predict a star’s brightness and reacts to any systematic deviations, like an anomaly detector.
Methods
ExoVeil’s core is a Transformer neural net (6 layers, 8 attention heads) trained to predict the next brightness data point from the entire past history. To make transits maximally anomalous, during training segments with known planets were masked and replaced with interpolated background — the model never saw actual transits. Trained on photometry curves of 16,499 stars, including sun-like and red dwarfs, the model then computes residuals, which are processed by a matched filter weighted by inverse prediction variance, enhancing sensitivity on quiet stretches and suppressing noise. False alarms like eclipsing binaries with white dwarfs are filtered by an XGBoost classifier on 21 features, and conformal prediction yields formal coverage guarantees for candidate ranking.
Results
A blind search among 3,737 Kepler stars flagged 179 transit-like anomalies not in the DR25 catalog; however, visual checks revealed some are caused by post-flare cooling, tracking errors, and edge effects. In a single-transit injection test, ExoVeil recovered 32% of events at 1000 ppm depth — while traditional classifiers can’t operate without phase-folding. Transferred to TESS data without retraining, the system detected all 47 confirmed planets in the PLATO LOPS2 field, including long-period and small ones. PLATO cadence simulations (25-second exposures) showed sensitivity reaches 100 ppm, entering the Earth-analog regime. All these results, however, need follow-up spectroscopy for confirmation.
Implications
The new approach tears down the barrier between detection and classification. It’s especially valuable for finding long-period planets that traditional methods miss, effectively doubling the usable observation window. Planet hunting in our Galaxy is entering a new era. Moreover, conformal prediction’s formal guarantees help allocate costly telescope time more efficiently for confirmation. Down the road, as atmospheric spectroscopy based on Rydberg laws matures, such candidates could become targets for biomarker searches — water, methane, and carbon dioxide — in their atmospheres.
Future development
The method will evolve along several fronts: boosting sensitivity via lighter architectures (e.g., Mamba instead of Transformer) for processing full light curves; integrating with PLATO simulations to precisely gauge performance in the Earth-analog domain; and building hybrid systems that blend prediction with classification. A key step will be automated recognition and culling of known false-alarm classes.
Impact
This will directly shape the data processing pipelines of future missions (PLATO, ARIEL), ground-based follow-up strategies, and telescope time allocation.
Next steps
Immediate steps include validation on simulated PLATO data (PlatoSim), adding automated false-positive rejection filters, and confirming candidates through radial velocities that exploit the Doppler effect.
Key open problems
The results feed directly into modern astrophysics’ central quest: finding potentially habitable worlds and gauging the prevalence of life in the Universe.
The knowledge machine's view
This section is addressed to the author of the paper and their colleagues. Neighbouring works were found by meaning-based search across our archive, not by word overlap. We do not review: we show the field around the work.
What the work does
ExoVeil trains a transformer to predict a star's brightness while masking known transits, and flags single events as deviations from those predictions. The method was tested on Kepler and TESS data, achieving sensitivity down to 100 ppm in PLATO simulations, and incorporates conformal prediction to rank candidates.
Where its strength is
Its key strength is the ability to catch single transits without knowing the period, opening the door to long-period planets that classical methods miss.
Where it could go next
- It might be interesting to see how the method handles false positives from stellar activity: nearby in the archive there's an analysis that removes mirages by comparing against a stationary reference.based on: The Still Stone Amid Dancing Mirages: How to Find an Exoplanet Among Illusions arXiv:2607.15973v1
- To extend the idea of confirming candidates with spectroscopy, one could explore neural network analysis of atmospheres: there's a related paper where a neural network tastes the atmospheres of distant planets.based on: A neural network tastes the atmospheres of distant planets arXiv:2603.27623
Worth trying
- Test whether adding stellar variability features to the XGBoost classifier reduces false positives from post-flare cooling.
- Apply ExoVeil to TESS data to hunt for single transits around red dwarfs, where transit depth may be larger.
- Use conformal prediction to dynamically allocate observing time for candidate confirmation.
Why this may matter
If the method scales to PLATO data, it could substantially expand the sample of long-period planets, including Earth analogs, which matters for future habitability studies.
Nearby works in our archive
- How to Spot a Pale Planet in a Star's Blinding Lightsimilarity 0.67
- Earth's Shadow Hunts for Alien Probessimilarity 0.66
- A Sun-Sized Lens Searches for Life Around Distant Starssimilarity 0.64
- Dark Matter Sways Distant Planetssimilarity 0.62
- A neural network tastes the atmospheres of distant planetssimilarity 0.62
- How to Hear a Planet Near a Dead Starsimilarity 0.61
- The Still Stone Amid Dancing Mirages: How to Find an Exoplanet Among Illusionssimilarity 0.61
The closest work in the archive sits at 0.67 by meaning — the usual level for our corpus.
Original abstract
as written by the authors arXiv:2606.02778v3
I present EXOVEIL, a transit detection system that learns what a star's brightness should look like and flags when reality disagrees. Unlike existing systems that require phase-folded input, EXOVEIL operates on raw flux time series and can detect planets that transit only once.A Transformer world model, trained on 16,499 Kepler light curves with transit-masked self-supervised learning, predicts expected stellar flux. A matched-filter detector with variance weighting extracts transit signals from the prediction residuals. A learned classifier (XGBoost) separates planets from false positives, achieving AUC 0.938 on Kepler DR25. Applied to single-transit injection-recovery, EXOVEIL recovers 32% of transits at 1000 ppm depth a task where all classification-based systems score 0% by construction. A blind search of 3,737 Kepler stars yields 179 new transit-like signals not present in the DR25 TCE catalogue, including 46 monotransit candidates. Applied withoutretraining to 47 confirmed TESS planets in the PLATO LOPS2 field, EXOVEIL achieves 100% recovery, demonstrating zero-shot cross-mission transfer. At PLATO's 25-second cadence, detection reaches 100 ppm -- approaching the Earth-analog regime. I provide the first application of conformal prediction to transit detection (95.9% empirical coverage) and release the system as pip install exoveil with pretrained weights and a candidate catalogue.
Fun fact: the first detector version, running on hand-crafted rules, scored an AUC of 0.36 — worse than random (0.5). It turned out that eclipsing binary residuals were deeper than planetary ones, so the system treated them as ‘more reliable’ signals.
Key numbers
- Trained on Kepler stars: 16,499
- Recovery of single transits (1000 ppm): 32%
- New candidates in blind search: 179
- Recovery of TESS planets (LOPS2): 100% (47/47)
- Detection depth at PLATO cadence: 100 ppm