Machine Learning Model Developed to Identify Promising Exoplanet Candidates Across Different Space Telescopes
Researchers have developed EXOVEIL, a machine learning system capable of detecting exoplanets from just a single observed transit event in stellar brightness data. Unlike conventional methods that require multiple transits to confirm a planet candidate, EXOVEIL trains a Transformer model to predict normal stellar flux and flags deviations as potential transit signals. The system could significantly expand the search for long-period planets, including Earth-like analogs, that current detection pipelines systematically miss.
EXOVEIL is a new exoplanet transit detection system that uses a Transformer-based 'world model' trained on 16,499 Kepler light curves via self-supervised learning to predict expected stellar brightness, then identifies anomalies in the residuals as potential planetary transits. A matched-filter detector and an XGBoost classifier work in tandem to separate genuine transit signals from false positives, achieving an AUC of 0.938 on the Kepler DR25 dataset. Critically, the system operates on raw flux time series rather than phase-folded data, enabling it to detect planets that transit only once — a regime where all classification-based systems score 0% by design. In single-transit injection-recovery tests, EXOVEIL recovered 32% of transits at 1,000 parts-per-million depth. A blind search of 3,737 Kepler stars uncovered 179 transit-like signals absent from the existing DR25 catalogue, including 46 monotransit candidates. The system also demonstrated zero-shot transfer to TESS data, achieving 100% recovery of 47 confirmed TESS planets in the PLATO LOPS2 field without retraining, and at PLATO's 25-second cadence it reaches 100 ppm sensitivity — approaching the threshold needed to detect Earth-analog planets. The authors additionally introduce the first application of conformal prediction to transit detection, providing statistically rigorous uncertainty quantification, and have released the system as an open-source Python package.
What's missing
The study is a preprint posted to arXiv and has not yet undergone formal peer review, so its results have not been independently validated. The 32% single-transit recovery rate, while a marked improvement over zero, means the majority of single-transit events are still missed; the paper does not fully characterize what physical or observational factors drive non-detections. The 179 new transit-like signals and 46 monotransit candidates are explicitly framed as anomalies requiring follow-up, and none have been confirmed as planets. It is also unclear how the system performs on stellar types or variability regimes not well-represented in the Kepler training set.
What different sources said
- arXiv cs.LGCenter
One Transit Is All You Need: Detecting Exoplanets Through Learned Stellar Behaviour with EXOVEIL
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.