A team from the Environmental Molecular Sciences Laboratory published research, demonstrating that the soil microbes were directly involved in the stabilization of soil organic carbon and mineral weathering.

Scientists have taken a key step toward harnessing a form of AI known as deep reinforcement learning to protect computer networks.

The work by the team at PNNL takes a critical step in leveraging ML to accelerate advanced manufacturing R&D, specifically for manufacturing techniques without access to efficient, first-principles simulations.

PNNL scientists carve a path to profit from carbon capture by creating a system that efficiently captures CO2 and converts it into one of the world’s most widely used chemicals: methanol.

A new approach broadens the reach of quantum computers to previously challenging systems.

PNNL mathematician Aaron Luttman contributed to the organizing committee for workshop exploring robust machine learning and artificial intelligence systems for the U.S. Army.

A collaborative effort led by PNNL researchers analyzed decarbonization pathways for Argentina, Chile, Egypt, Indonesia, and Nigeria.

The Joint Appointment program at PNNL is one of the most diverse among other U.S. national laboratories, involving nearly 60 universities and research institutions in the United States and abroad.

A review article led by researcher Jade Holliman explores the different classes of metamaterials, from the underlying fundamental science to potential applications.

Researchers developed a machine learning model that can analyze chemical reactions as they happen in an electron microscope.

Steven Spurgeon’s research is featured in the cover of the MRS Bulletin along with his team’s invited perspective on the future of machine learning for electron and scanning probe microscopy.

A PNNL team developed and used a model framework to understand the performance and structural reliability of a state-of-the-art solid oxide electrolysis cell design.

Iron-based fertilizer may stimulate plankton to pull carbon dioxide from the ocean, driving a carbon-negative process.

As leaders in AI and machine learning, PNNL experts are sharing their latest findings at the 36th annual Neural Information Processing Systems (NeurIPS) Conference, Nov. 28–Dec. 9, 2022.

A new project will produce a database of optimized conditions for efficient, carbon negative recovery of energy-relevant minerals in red mud waste.

PNNL gathered researchers from eight national laboratories plus the U.S. Department of Energy (DOE) to share ideas and build synergy at the Energy Equity and Environmental Justice Summit.

A review article examines a decade of work on the atom-scale process of turning carbon dioxide into stable minerals.

PNNL researchers use machine learning and data analytics to assist with detection of nuclear proliferation and nuclear material trafficking.

HiSVSIM enables large-scale quantum simulations through graph partitioning.

Some rocks can potentially convert injected carbon dioxide into more stable solid minerals. A new review article explores what scientists know about the atom-by-atom process.