Models have identified a new source of anthropogenic emissions driving the observed weakening of the Atlantic Meridional Overturning Circulation.

ChatGrid™ is a practical application of the Department of Energy’s exascale computing efforts and offers a new experience in easy, intuitive, and interactive data interaction.

The physics-informed machine learning optimization framework is now PNNL’s most popular open-source repository on GitHub.

PNNL researchers use chemometric analysis to model chemistry in molten salt.

Ang participated in a White House-hosted CHIPS R&D event and roundtable discussion with senior leaders from industry, academia and key government agencies.

Identifying how curvature affects the doping and hydrogen binding energies of carbon-based materials provides a framework for designing hydrogen storage materials.

Post-consumer recycled aluminum to be transformed into high strength building materials and consumer goods with patented ShAPE™ manufacturing process.

Machine learning methods and data science can uncover hidden patterns in nanoparticle synthesis conditions and property outcomes.

At the GovAI Summit 2023, Ryan Eddy joined the Department of Homeland Security Science and Technology Directorate on a panel highlighting artificial intelligence impacts and opportunities in the field of emergency management.

The convergence of artificial intelligence, cloud, and high-performance computing to accelerate scientific discovery is the focus of a multi-year collaboration between Microsoft and PNNL.

From energy storage to cybersecurity, this 2023 wrap-up offers a glimpse of PNNL innovations with a seasonal twist.

Now in its twentieth year, the Hydrogen Safety Panel is led by PNNL and includes more than two dozen experts. These experts developed a trusted resource for best practices for hydrogen energy.

An initiative from Washington State University and Snohomish County leaders is aiming to make Paine Field a nexus for testing and improving sustainable aviation fuels made from non-petroleum materials.

A newly developed, highly conductive copper wire could find applications in the electric grid, as well as in homes and businesses. The finding defies what's been thought about how metals conduct electricity.

PNNL researchers comment on the “Adversarial Machine Learning” white paper from the National Institute of Standards and Technology.

PNNL has created the Center for AI @PNNL to coordinate the pioneering research of hundreds of scientists working on a range of projects in artificial intelligence.

A seemingly simple shift in lithium-ion battery manufacturing could pay big dividends, improving electric vehicles’ ability to store more energy per charge and to withstand more charging cycles.

PNNL is one of the founding partners of the Trillion Parameter Consortium, which was formed to create reliable generative AI models.

Input from humans helps when deciding whether to trust the recommendations or decisions of a machine-learning system.

Researchers created a methodology to design custom network topologies that improve the execution time for scientific applications.