Improving a snow albedo model to account for non-spherical snow grain shapes and the mixing of dust inside snowflakes in an Earth system model.

Building new climate outcome scenarios by stitching together pieces of existing ones.

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.

The flux of carbon dioxide from forest soil may acclimate to some aspects of climate change.

Identifying links between large-scale and local-scale model biases in tropical precipitation.

Interactive freshwater flux works to prolong density anomalies over deep water formation areas in the North Atlantic.

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

Interactions between fronts and the land-sea breeze lead to strong vertical exchange in the northern Gulf of Mexico.

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.

Data-driven experiments can help determine best practices for Random Forest machine learning to predict water quality, particularly nitrate levels.

When wildfires burn in the west, the heat and airborne particles they release inflict stronger rain and larger hail upon central states.

Evaluating the relative roles of soil water stress and vapor pressure deficit at limiting canopy conductance in coupled land-atmosphere simulations.

Understanding why the westerly jets shift poleward in certain seasons and regions but equatorward in others under global warming.

PNNL joint appointee Auroop Ganguly uses data science to study the impacts of climate change.

Across the United States, water moving between the river and riverbed sediments does not overcome localized processes that govern organic matter chemistry.

Two case studies of clouds evolving over the Arctic provide data that will help researchers evaluate cloud simulations.

Evaluating the accuracy of predicted plant aboveground biomass with different numerical solution options in a model of water transport in plants.

How hailstorms respond to human-created warming in the Great Plains depends on large-scale weather-producing systems.

The presence of mMarine microorganisms may enhance cloud droplet formation, leading to brighter clouds that reflect more sunlight.

Observational evidence shows that clouds strongly influence the seasonal heat exchange between Southern Ocean air and sea.