PNNL researchers have shown an improved binarized neural network can deliver a low-cost and low-energy computation to help the performance of smart devices and the power grid.

Historical weather data informs projections of global yields of economically important crops.

To accurately model future U.S. agricultural production, changes in international crop yields cannot be ignored.

Researchers introduced a simulated carbon cycle to the Energy Exascale Earth System Model, broadening its utility and enabling new research directions.

Ecosystem feedback fire model opens new investigative pathways into impacts of fire on future climate.

Hybrid land use model incorporates key factors to understanding agriculture’s potential response to climate change.

Differences in the rainfall intensity of mesoscale convective systems and other types of warm—season rainfall in the central United States lead to differences in their impacts over land.

PNNL and Microsoft Quantum partner to link quantum circuits to powerful government supercomputers.

Atmospheric rivers that make landfall on the U.S. West Coast show broad increases in size and intensity with warmer local sea surfaces.

Floodplain inundation simulations shed light on flood generation mechanisms and the increasing role of extreme rainfall.

Pacific Northwest National Laboratory researchers developed a graphical processing unit (GPU)-centered quantum computer simulator that can be 10 times faster than any other quantum computer simulator.

Information extracted from a variety of atmospheric observations can correct the behavior of a model and improve simulated clouds.

PNNL’s new Smart Power Grid Simulator, or Smart-PGSim, combines high-performance computing and artificial intelligence to optimize power grid simulations without sacrificing accuracy.

The MIT-sponsored competition encourages community approaches to developing new solutions for analyzing graphs and sparse data; PNNL has placed a winner in each year.

Aerosol treatments in E3SM affect clouds, heat reflected to space, and Earth’s snow-or-ice-covered surface.

Researchers created an open database for soil-atmosphere greenhouse gas flux data.

PNNL researchers used the Global Change Analysis Model (GCAM) to explore 15 different global scenarios that consisted of combinations of five different socioeconomic futures and four different climatic futures.

New-particle formation driven by natural biogenic emissions produces a large number of small particles in the Amazon free troposphere.

Tracking down nefarious users is just one example of work at PNNL’s Center for Advanced Technology Evaluation, a computing proving ground supported by DOE’s Advanced Scientific Computing Research program.

Pacific Northwest National Laboratory researchers used machine learning to explore the largest water clusters database, identifying—with the most accurate neural network—important information about this life-essential molecule.