From guesswork to guidance: How machine learning speeds dopant design for water-splitting photocatalysts

MLIP calculations successfully identify suitable dopants for a novel photocatalytic material, report researchers from the ...
Phys.org

Enhancing machine-learning interatomic potentials for advanced materials modeling

Machine learning is transforming many scientific fields, including computational materials science. For about two decades, scientists have been using it to make accurate yet inexpensive calculations ...
Science Daily

Novel machine learning model can predict material failure before it happens

A team of researchers has successfully predicted abnormal grain growth in simulated polycrystalline materials for the first time -- a development that could lead to the creation of stronger, more ...
Medicine Buffalo

AI-Guided Material Discovery: Unsupervised Learning and Data Science for Safer, High Performance Material Discovery

Join us to learn about how to use cutting edge GPU infrastructure to solve real world material discovery problems with AI and unsupervised machine learning. Our lab in the Department of Materials ...
Nanowerk

Interpretable machine intelligence for materials design of metal hydrides

Hydrogen storage is limited by high pressure or cold tanks. Metal hydrides offer efficiency. A large curated database reveals key atomic traits to guide design. (Nanowerk News) Hydrogen fuels ...
Nanowerk

Strong as steel, light as foam: Machine learning and nano-3D printing create breakthrough nano-architected materials

(Nanowerk News) Researchers at the University of Toronto’s Faculty of Applied Science & Engineering have used machine learning to design nano-architected materials that have the strength of carbon ...
EurekAlert!

Machine learning ushers in a new era for advanced nuclear materials research

Shanghai, August 21, 2025 — Nuclear energy is widely recognized as one of the most promising clean energy sources for the future, but its safe and efficient use depends critically on the development ...
Michigan Technological University

Researchers Apply Machine Learning and AI in Search of Less Costly Electronic Structure Method

Electron density prediction for a four-million-atom aluminum system using machine learning, deemed to be infeasible using traditional DFT method. × Researchers from Michigan Tech and the University of ...
Semiconductor Engineering

Machine Learning Tools Help Bridge Design-To-Manufacturing Gap

More aggressive feature scaling and increasingly complex transistor structures are driving a steady increase in process complexity, increasing the risk that a specified pattern may not be ...