AM-IA brings together news, research papers and applications relating to artificial intelligence published around the world into a single feed — and makes them available in your European language at the click of a button.
Scroll to browse · Click to filter
By combining spectra, light curves and images from VizieR and IRSA, the classifiers identify young stars with over 90 per cent accuracy and rule out outliers with over 99 per cent accuracy.
Trained on 111,000 simulated images, the model extracts the n=1 ring hidden beneath the main emission with a correlation of approximately 0.99, with a view to future missions such as BHEX.
Velocity and magnetic field are removed from the drive, then reintroduced as diagnostics. The geometry learned on morphology is however ordered according to these quantities.
LUMA combines physics-inspired pretreatment, which brings out bows and tenus rings, with a compact network — and achieves 96% accuracy on simulated data.
The start-up TakeMe2Space embeds Nvidia Orin NX chips to process images directly in space and send back only the results. Launch scheduled for October 1.
A refrigerator-sized satellite, dubbed MVP, is set to launch from Vandenberg on SpaceX's Transporter-18 mission to test calculation, radiation and heat dissipation.
Michelle Lochner defends partial automation in the face of the volumes of the SKA and the Vera C. Rubin Observatory: it is the interface between algorithm and expert that produces the discoveries.
The system, built on a Transformer architecture, reads about 2,500 sensors to diagnose the status of the spacecraft and trigger maneuvers, without going through ground crews.
Loft Orbital and Emirati investor Marlan Space want to fly 50 optical and radar satellites with AI on board, with models provided by French start-up Mistral.
Classification of galaxies, sorting of SETI signals, reconstruction of black hole images: astronomer Chris Impey details the uses that have become routine in front of the data flood.
Gathered for World Space Business Week, managers from Eutelsat, Esri and Space42 describe the shift from an analysis tool to systems that decide.
Temasek and Seraphim lead the Indian company's funding round, which brings its total funding to $192 million and is preparing a second generation of satellites.
The ASTRA program has had a drone and two rovers work together in Virginia, letting them arbitrate between the physical risk and the scientific gain of an unforeseen discovery.
Loft Orbital and Marlan Space, based in Abu Dhabi, are entering a constellation whose image processing will be done on board, on GPUs, without lowering the data to the ground.
Trained on more than thirty layers of data from nine instruments and four missions, the model reduces the error in detecting lunar ice deposits by up to 22%.
An article on Google Developers explains how neural networks use detector tracks to study particles from space.
Falcon 9's 90th flight this year: 57 Starlink satellites and two small commercial reconnaissance satellites took off together from the Kennedy Space Center.
A model trained on the light curves recorded by telescopes distinguishes a rotating satellite from a tumbled satellite, and signals 88% of abnormal behaviour to operators.
NASA had a satellite of the Starling mission calculate its own orbit by recognizing debris and neighboring craft with a stargazette, without any GPS signal.
On 125,000 acres on Pecan Island, "Starbase, Louisiana" is expected to host thousands of Starship flights per year, with the first launch targeted in 2029.