Machine-Learning

In 2023 the VLT Survey Telescope on Cerro Paranal recorded 1,246,048 CCD frames with its OmegaCAM imager. A team led by Elisabeth Rachith at EPFL ran all of them through a deep-learning streak detector, and their June 2026 preprint reports 25,335 streaks from satellites, rocket bodies and debris, with at least one in 16.9% of exposures. In the months checked by hand, about a fifth of the confirmed streaks matched nothing in the public satellite catalogue. Below: how these networks work, what the VST numbers say, and why a stack of backyard subs mostly doesn’t need one. ...

The Dark Energy Camera Legacy Survey imaged about 1.6 billion sources. Even after aggressive quality cuts, that leaves nearly four million galaxies, far more than any team will ever eyeball. The discoveries hiding in a catalog that size are usually not the objects someone built a detector for. They’re the ones nobody thought to name: a galaxy bent into a ring, a gravitational lens that slipped past the catalogs, a pair caught mid-collision. A small family of tools now goes looking for exactly those, and the trick behind all of them is the same. Let one person teach an algorithm what “interesting” means, then let the machine apply that taste to millions of images. ...

Running a full atmospheric retrieval on a JWST transmission spectrum of WASP-39b took about 498 hours of compute with standard settings, roughly three weeks of a core grinding away. A new transformer neural network gets the same answer in about 64. Same retrieval code, same Bayesian machinery, same posterior at the end. It just starts the search in a far better place. The paper is Exoformer: Accelerating Bayesian atmospheric retrievals with transformer neural networks, led by L. Pagliaro and published in Astronomy & Astrophysics this spring. I spent years training neural nets before I started pointing a Seestar off my balcony in Nicosia, and what I like about this one is what it refuses to do. It doesn’t hand you an answer from a black box you can’t check. It speeds up the slow, principled method by giving it a good first guess. ...

Euclid’s first quick data release covered 63 square degrees, about 0.45% of the sky the mission will eventually map, and in that sliver it turned up 497 galaxy-galaxy strong gravitational lenses. Of those, 250 are grade A candidates, and 243 had never been published before. In one fraction of one percent of the survey, the team doubled the number of strong lens candidates ever found with space-based imaging. That’s the headline. The part I keep coming back to, as someone who spent years training image classifiers before I spent my evenings pointing a Seestar off a Nicosia balcony, is how they did it. It wasn’t one clever network. It was five different neural networks feeding a funnel of human eyes, and the honest lessons about which models worked, where they failed, and why you still can’t cut the humans out are more interesting than the pretty arcs. ...

In three nights the Perseids peak under a new moon, the darkest Perseid maximum in five years. I’ll be up at Troodos with a reclining chair and a tally sheet, counting by eye the way people have counted meteors for a century. Overhead, a network of more than 1,300 cameras will be counting too, and solving an orbit for every meteor bright enough to trigger two of them at once. What made that automation possible is a piece of software: a neural network that learned to tell a meteor from an aeroplane. ...

You give it a sentence — “measure the cosmological parameters from this supernova dataset” — and walk away. About 30 language-model agents pick it up, search the literature, write the analysis code, run it, read the output, argue with each other about whether the answer is sound, and hand back a result. No human touches the keyboard in between. The team that built this calls the demo “a PhD level cosmology task,” and the system did it end to end. ...

Here’s the number that made me put my coffee down. A model trained on Euclid galaxy images matched a fully supervised network at estimating galaxy redshifts and stellar masses — using 1% of the labeled examples. Ninety-nine percent of the labels thrown away, same accuracy. That result is from the Euclid Quick Data Release paper by Siudek et al., published in Astronomy & Astrophysics on 30 June 2026. It’s one of three papers from the last two years that convinced me astronomy has quietly acquired what the machine-learning world calls foundation models: a single large model pretrained once on a mountain of unlabeled data, then adapted cheaply to many different tasks. ...

A paper published in the Journal of Cosmology and Astroparticle Physics on June 10 asks a deceptively simple question: if you train a neural network on the standard cosmological model and then ask it to look for physics beyond that model, does the pretraining help or hurt? The answer, from a Princeton and Flatiron Institute team, is both. Transfer learning — pretraining on cheap ΛCDM simulations, then fine-tuning on expensive beyond-ΛCDM runs — cut the number of simulations needed by more than a factor of 10 in some scenarios. But it also introduced a failure mode the authors call negative transfer: the network learned the standard model’s patterns so thoroughly that it confused genuinely new physics with familiar old parameters. ...

A team at Tsinghua University built a neural network called ASTERIS that strips structured noise from telescope images, without ever seeing a clean reference frame. Applied to JWST deep-field data, it recovered galaxies one full apparent magnitude fainter than previous pipelines could detect, and tripled the number of galaxy candidates at redshifts above 9. The paper landed in Science in April 2026, and the code is on GitHub. One magnitude sounds modest until you remember the scale is logarithmic. A gain of 1.0 mag means detecting objects 2.5× dimmer. That’s roughly equivalent to doubling the mirror area of the telescope that took the data. ASTERIS achieves it with software alone. ...

On February 25, 2026, the Vera C. Rubin Observatory in Chile sent its first batch of real-time alerts — 800,000 of them in a single night. Each one flagged something that changed in the sky: a new point of light, a brightening star, a moving dot that might be an asteroid. The Legacy Survey of Space and Time (LSST) had officially started talking. That was the gentle version. At full survey depth, Rubin will generate up to 10 million difference-image alerts every night. No research group, no observatory control room, no grad student with a caffeine problem can review that by hand. The only reason the alerts are useful at all is a network of nine community software platforms — called alert brokers — that run machine-learning classifiers on every packet before the Sun comes up. ...