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
Meteorologists in Munich re-use the model decoder to read their internal states during calculation: quality progresses layer after layer, from large scales to small ones.
A Transformer Vision that combines sky images and sun measurements reduces the forecast error by 9.6% to 30 minutes, a key horizon to balance solar production.
Researchers at the Barcelona Supercomputing Center offer a test bench that judges models on the rare pixels where land use changes, where the uncertainty of the carbon cycle is involved.
According to a study conducted under a common protocol, AI models miss more extremes when the physical model multiplies false alerts. Each metric penalizes one or the other error, hence conflicting conclusions.
By combining three types of on-board sensors on five geostationary satellites, this deep learning system aims to provide reliable rain data in time for flood warning.
By surveying the internal states of GraphCast on 205 cyclones, a team shows that each physical attribute is distributed over several characteristics, according to an organization that repeats itself from layer to layer.
Marc Bocquet and his co-authors replace the assumption of a Gaussian model error with a stochastic forecast learnt through data assimilation, yielding clear benefits when observations are incomplete.
According to this model, internal variability explains the bulk of the relative cooling of the equatorial Pacific since 1980 and the drying of southwestern North America.
This probabilistic transformation refines a numerical prediction through scattered observations and, downhill from ERA5, does better than the COSMO model on temperature and rain.
By separating weather data from pollutant chemistry, this Swin-Transformer-type model forecasts air quality up to five days in advance and outperforms CAMS on all variables beyond 48 hours.
Selecting mostly rainy episodes to train and test models can reverse the diagnosis: the same model seems too cautious or too alarmist depending on the test set.
Twelve Xe-100 modular reactors with a combined capacity of 960 MW, operated by AEP near Terre Haute: Amazon has tripled the scale of its first agreement with X-energy, even though the company’s pioneering reactor in Texas has not yet been launched.
Retrained on the UKCA chemistry-climate model, Aurora reproduces 23 out of 27 fields with an R² greater than 0.85 and learns to correct its ozone biases using MLS satellite data.
Having analysed 159 CMIP models since 1995, an EU roadmap quantifies the diminishing returns on computing and calls for standardised energy reports ahead of CMIP8.
Based on the GCAM integrated evaluation model, the environment was used to compare seven methods across 3,210 simulations; the CMA-ES evolutionary strategy emerged as the winner in all three scenarios.
Researchers have used large language models (LLMs) to map the literature on water and energy use in AI infrastructure, from mining to electronic waste. The conclusion: we mainly measure the electricity used by data centres, but the rest is poorly measured.
Palisades, Three Mile Island and Duane Arnold are set to supply 2.25 GW to the grid, with Microsoft and Google as customers. Critics have raised concerns about the safety of reactors designed in the 1970s.
By incorporating penalties for local maxima and gradients into the training process, researchers have improved the super-resolution of 150 out of 168 wind fields, with topological deviations reduced by between 25 and 31 per cent.
The U-Net model used to clean the KaRIn altimeter measurements produced artefacts in conditions of heavy swell or in the presence of internal waves. A new training procedure corrects these biases.
Oracle’s AI campus in New Mexico is set to see its permitted annual greenhouse gas emissions reduced from 8.8 to 5.7 million tonnes; opponents are demanding to see the calculation models.