A new study uses direct numerical simulations to develop a near-surface turbulence model for thermal convection using interpretable and physics-aware neural networks, broadening the applications of numerical simulations.

A PNNL study developed a water management module for Xanthos that distinguishes between the operational characteristics of hydropower, irrigation, and flood control reservoirs.

The Earth System Model Aerosol–Cloud Diagnostics package version 2 uses aircraft, ship, ground, and satellite measurements to evaluate detailed physical processes in aerosols, clouds, and aerosol–cloud interactions.

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.

With the help of the U.S. State Department, PNNL climate scientists assisted counterparts in Malaysia and Thailand in exploring carbon neutral goals.

PNNL helps deliver efficiency-related rules and requirements that steadily improve performance of America’s buildings, saving energy and costs and reducing carbon emissions.

Pacific Northwest may face increase in summer heat-dome-like stationary waves.

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

New research shows how cloud shapes affect the process of cloud evolution, resulting in better understanding of how clouds behave, improving weather forecasts, and enhancing comprehension of climate systems.

Earth Scientist Laura Fierce mentors Department of Energy Science Graduate Student Research program awardees.

As electricity grids incorporate renewables, several factors will constrain future output, according to a new paper.

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

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

Scientists recently developed a flow direction model which produces high-quality flow routing parameters on any mesh system.

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

A larger HVAC workforce with training on modern heat pump technology will be pivotal to achieving the mass-scale electrification of household HVAC systems needed to meet building decarbonization goals.

Researchers from PNNL, CSET, and Google DeepMind delved into the potential risks of artificial intelligence in a roundtable discussion.

Leaders from the DOE Office of Energy Efficiency and Renewable Energy visited PNNL October 19–20 for a firsthand look at capabilities and research progress.