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
Tested on 15,000 signals injected into real data from the Green Bank telescope, a CNN detector sees its recall plummet as the signal becomes stronger and fails to recognise the patterns that would allow it to filter out interference.
By modelling each fragment as a node and replacing additive aggregation with multiplicative aggregation, researchers are able to track these structures as they break apart and merge more reliably.
On simulated data, convolutional network inversion outperforms the conventional algorithm, particularly when the signal is weak and the exposure time is short, paving the way for rapid mapping of the entire sky.
Trained on around 2,600 known nebulae from the IPHAS and VPHAS+ surveys, a model developed by a French team achieves a recall of 97.4 per cent, but still struggles with HII regions that resemble them.
Out of 872,228 light curves from Gaia DR3, the anomaly detection process has identified 8,504 instances of unusual behaviour, including 682 nuclei that appear to alternate between two brightness levels.
By classifying ten equations of state based on noisy data from several detectors, the study shows that the geometry of the network of observatories has a significant impact on the result.
To find out whether a machine learning model is better at predicting turbulence above large telescopes, a point of comparison is needed: one team proposes two such points.
Rather than predicting the temperature point by point, researchers are compressing atmospheric temperature profiles into latent space – the first step towards more consistent and faster emulators.
Trained on 568,127 arcs from 39,031 real-world objects, a physics-informed model proposes a plausible orbit in 85 per cent of cases, compared with around 45 per cent for the Gauss and Laplace methods.
Rather than relying on a single algorithm, a classifier utilises the signals – or the absence thereof – from all the pipelines to better distinguish between noise and genuine events, and to reduce false alarms.
An agent trained using simulation mediates between the competing objectives of the European mission and adapts to an expanded catalogue or a new scenario without the need for further training.
By adapting the Surya foundation model, researchers are synthesising SDO/AIA-type images from observations in the He I 10830 Å line, which have been available for much longer.
By controlling the manoeuvre probability via an independent filter, the RD-IMM method detects discrete thrusts in geostationary orbit and reduces the position error by more than half.
Researchers propose pre-calibrating the PO4AO controller using an internal light source, in order to correct for turbulence without the need for a linearly stable controller.
Without deep learning, the method constructs a coordinate system based solely on the stellar spectra from APOGEE and DESI, and then applies the labels from a few stars to all the others.
On simulated observations of XMM-Newton, a CNN working directly on photon-by-photon event cubes proves to be the most robust classifier for extended and weak X-ray sources.
Using a simplified model of a pulsar array, four researchers explain why simulation inference detects gravitational wave background anisotropies better than conventional statistics.
Applied to LSST Data Preview 1 data, DeepDISC detects, separates, and classifies stars and galaxies in a single pass, with galaxy completeness increasing from 40% to 84% after adjustment.
Trained solely on synthetic spectra, the pipeline processed 274,721 red giant candidates and identified the ‘red clump’ without ever having been provided with evolutionary labels.
On the first large Cherenkov telescope at the future CTAO observatory on La Palma, a neural network analyses the complete image of atmospheric showers, whereas standard analysis relies on just a few parameters.