A hybrid physics-informed neural network extracts concrete fracture parameters from stress images with an error margin of ...

Hybrid climate modeling has emerged as an effective way to reduce the computational costs associated with cloud-resolving models while retaining their accuracy. The approach retains physics-based ...

Running a single physics simulation can take hours or days, depending on the complexity of the geometry and the equations involved. For engineers iterating through hundreds of design variations, that ...

Scientists found that transfer learning can make the search for new physics in the universe much faster, slashing the need for expensive simulations. Yet the approach can backfire when AI relies too ...

On the same day IEEE Spectrum reported that General Motors had compressed two weeks of aerodynamics analysis into a matter of minutes using AI trained on simulation data, the broader field that made ...

A study in the Journal of Cosmology and Astroparticle Physics explores how a machine-learning strategy known as transfer learning could dramatically reduce the computational cost of searching for new ...

Wildfire AI hazard mapping: Mila and Natural Resources Canada have released an open-source emulator that reproduces months of ...

Design engineering is running headfirst into a materials bottleneck. Industries such as automotive, aerospace, electronics, and semiconductors now depend on increasingly complex materials. Yet ...

During surgery to correct an abnormal heartbeat, doctors rely on a mix of imaging and inference. Still, many critical details remain hidden. At RIT, artificial intelligence (AI) researchers want to ...

Researchers in Argentina have built a two-stage AI pipeline that generates realistic abdominal ultrasound images from simple ...