AI for Good event commemorates 60 years of community engagement, features AI applications, and offers practical AI tools to empower people.

This achievement earned DIMPLES a Best Paper award at the ACM International Conference on Supercomputing 2025.

Christina Lomasney moderates panel on commercialization pathways for emerging artificial intelligence and high-performance computing technologies.

More than 25,000 participants from industry, government, academia, and the public attended the event.

A new time-dependent wavefunction formulation for the cumulant Green’s functions can produce more accurate simulations.

Neural networks techniques enable the efficient capture of electron correlation effects in reduced-dimensionality spaces.

The Center for Continuum Computing at PNNL aims to integrate cloud platforms, high-performance computing, and edge devices into a seamless ecosystem that accelerates scientific discovery.

Developing a new scheme to more efficiently solve quantum chemistry problems.

PNNL chemical engineer Mariefel Olarte shares passion for mentoring students and the next-generation workforce.

PNNL Program Development Office Director Karl Mueller explains how the TEC4 project seeks to make advanced chemical computations accessible to all.

Electronic structure codes in a cloud environment can enable efficient computational chemistry simulations.

CACTUS provides AI-powered cheminformatics for autonomous science.

PNNL’s Center for Cloud Computing is addressing challenges in data management and hybrid cloud solutions with industry and academic partnerships.

The Testing Risks of AI for National Security Taskforce will address critical safety and security concerns related to artificial intelligence.

Pacific Northwest National Laboratory researchers developed a new theoretical method for studying highly correlated systems.

PNNL researchers work with industry partners to transform large language models.

University of Washington Professor David Baker won the 2024 Nobel Prize in Chemistry for computational protein design.

Pacific Northwest National Laboratory scientists discussed their materials research at Accelerate’24.

PNNL researchers have developed a new, physics-informed machine learning model that accurately predicts how heat accumulates and dissipates during friction stir processing.

ChemReasoner combines decades of chemistry knowledge with large language models to propose strategies for effective new catalysts.