The Lab’s newly formed Center for AI, in partnership with NVIDIA, recently hosted a joint “LLM Day.” During the day, NVIDIA AI experts engaged with PNNL scientists on opportunities to make generative AI a powerful tool for science.
A new study demonstrates a hybrid model that can simulate part of a system at the molecular scale and other parts at larger scales in a computationally efficient manner, providing greater simulation flexibility.
PNNL played host in mid-May to the Artificial Intelligence for Robust Engineering & Science workshop, an annual event that explores advances in artificial intelligence
A PNNL Deep Vadose Zone Program publication that shows ferrihydrite helps protect groundwater is featured on the cover of ACS Earth and Space Chemistry.
New research investigating water-lean solvents for carbon dioxide capture identifies the unique chemistry possible with their use, may lead to new design principles that move beyond single carbon capture.
Long-range electron transfer reactions play important roles in many chemical and biochemical processes. A new study demonstrates that a common organic host molecule can behave like an alkali metal in long-range electron transfer reactions.
With her broad experience and background, Starr Abdelhadi was selected from many applicants to join the Women in IT Networking at SC (WINS) program for Super Computing 2024 (SC24).
Scientists at PNNL harnessing advances in deep learning, deep reinforcement learning and generative AI to change how science is conducted and achieve original scientific results and breakthroughs.
Twinned nanocrystals have unique physical and chemical properties, a variety of which are detailed by a new study. These findings can help guide future efforts in controlling twinning and detwinning in gold nanoparticles.
PNNL computing experts Robert Rallo and Court Corley contribute their knowledge to a recent DOE report on applications of AI to energy, materials, and the power grid.
A breakthrough in electron microscopy based on deep learning can automatically visualize and identify areas of interest, helping to speed advances in materials science.
Practical decontamination of industrial wastewater depends on energy-efficient separations. This study explored using ionic liquids as part of the process, enabling efficient electrochemical separation from aqueous solutions.