MIT researchers have created an AI model capable of classifying and quantifying atomic-scale defects in materials using noninvasive neutron-scattering data. The system can simultaneously detect multiple defect types in semiconductors and related materials, potentially advancing quality control and performance for industries such as electronics and solar energy.
Researchers at Virginia Tech and Johns Hopkins University have developed a data-driven, AI-powered framework to speed up the discovery of advanced metallic alloys for demanding environments. By combining explainable AI, machine learning, and high-performance computing, the team can efficiently identify promising alloy compositions. Their work highlights the shift from traditional trial-and-error experimentation to predictive AI-driven materials science.
Researchers have leveraged artificial intelligence to develop alternatives to rare earth magnets commonly used in electric vehicles. This innovation addresses concerns over supply chain risks and environmental impacts associated with rare earth mining. The breakthrough could enable more sustainable and cost-effective production of electric vehicle motors.
A team of scientists has unveiled the longstanding mystery behind the magnetic properties of steel, leveraging advanced AI-powered simulations. The research provides new insight into how microscopic structures shape steel's magnetic behavior, opening avenues for innovations in both industry and materials science.
A team of physicists has successfully observed a novel, intermediate state of matter—a breakthrough shedding new light on quantum phenomena and potentially informing advanced AI computations. The discovery, relevant for both theoretical physics and the future of material sciences, underscores the power of combining machine learning techniques with traditional experimental research.
Stay informed with curated insights delivered weekly to your inbox.