AI System Enables Semantic Search of 100 Million Galaxy Images, Discovers New Stellar Streams
Researchers have developed AION-Search, an AI pipeline that enables semantic text-based searching across more than 100 million unlabeled galaxy images. The system uses Vision-Language Models to auto-generate captions for galaxy images, then aligns an astronomy foundation model with those descriptions to create searchable embeddings without manual labeling. The tool achieves state-of-the-art zero-shot performance on rare phenomenon detection and has already identified 36 new extragalactic stellar stream candidates, demonstrating a scalable approach to scientific image discovery.
AION-Search is a newly developed AI pipeline designed to make large, unlabeled astronomical image archives semantically searchable at scale. The system works by using Vision-Language Models (VLMs) to automatically generate text descriptions of galaxy images, then contrastively aligning a pre-trained astronomy foundation model with those embedded descriptions to produce searchable vector representations. Crucially, the model was trained on randomly selected images with no deliberate curation for rare phenomena, yet still achieves state-of-the-art zero-shot performance in finding rare astronomical objects. The researchers also introduce a VLM-based re-ranking step that nearly doubles recall for the most challenging search targets within the top-100 results. As a proof of concept, the system identified 36 new extragalactic stellar stream candidates — faint structures that are extremely difficult to find through manual inspection. The code, data, and a public application are openly available, and the paper has been accepted for publication in The Astrophysical Journal. The authors note the approach generalizes beyond astronomy to other large scientific image archives, including Earth observation and microscopy.
What's missing
The study does not detail the false positive rate among the 36 new stellar stream candidates, nor whether any have been independently confirmed through follow-up observations. The paper does not fully characterize failure modes of VLM caption quality at the extremes of image quality or underrepresented galaxy morphologies. Scalability benchmarks (e.g., query latency across the full 100M+ dataset) are not described in the abstract.
What different sources said
- arXiv cs.AICenter
Semantic search for 100M+ galaxy images using AI-generated captions
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.