Researchers at PNNL have developed an interpretable, lightweight AI model that can easily predict weld microstructure features using only basic machine sensor inputs.

PNNL has developed a next-generation electrical resistivity tomography system for DOE that uses E4D software and AI-enhanced modeling to produce real-time subsurface images that help guide environmental remediation decisions.

RemPlex 2025 Global Summit on Environmental Remediation attendees share knowledge about cleanup and monitoring of complex sites worldwide; more than 100 presentations are posted online.

The ability of a storm-resolving weather model to predict the growth of storms over central Argentina was evaluated with data from the Clouds, Aerosols, and Complex Terrain Interactions (CACTI) field campaign in central Argentina.

Researchers have developed the first coastal transport model for microplastics to understand how particles move in waterways and coastal currents.

Researchers from PNNL and Parallel Works, Inc., applied machine learning methods to predict how much oxygen and nutrients are used by microorganisms in river sediments.

Lakes are important sentinels of climate change and contribute significantly to the emissions of the second most important greenhouse gas—methane.

The rate of conversion of cloud droplets to precipitation, known as the autoconversion rate, remains a major source of uncertainty in characterizing aerosol’s cloud lifetime effects and precipitation in global and regional models.

To assess the impact of observation period and gauge location, model parameters were learned on scenarios using different chunks of streamflow observations.

PNNL's E-COMP initiative is helping unleash American energy innovation with advanced theories, models, and software tools to better operate power systems that rely heavily on high-speed power electronic control.

This study presents an automated method to detect and classify open- and closed-cell mesoscale cellular convection (MCC) using long-term ground-based radar observations.

RemPlex and IAEA convene international leaders to tackle recruitment and retention in complex environmental cleanup efforts.

The Deep Vadose Zone program leads a treatability study for subsurface remediation of the Hanford Site’s Central Plateau.

PNNL’s Center for the Remediation of Complex Sites convened attendees from around the world to discuss challenges associated with environmental contamination.

Scientists at PNNL have published a new article that focuses on understanding the composition, dynamics, and deployment of beneficial soil microbiomes to get the most out of soil.

PNNL chemists investigate the performance of ion exchange resins for subsurface remediation of uranium, technetium, and chromium.

Through collaboration with the Department of Homeland Security Soft Target Engineering to Neutralize the Threat Reality Center of Excellence, PNNL is advancing research and development of tools and methodologies to protect crowded places.

Recovery Simulator and Analysis tool further strengthens PNNL’s short-term resilience planning efforts for Puerto Rico.

PNNL’s ARENA test bed analyzes how electrical cables degrade in extreme environments and how nondestructive examination inspection technologies can detect and locate damage.

ExaGO, a power grid simulation and optimization platform developed at PNNL is the first of its kind to run on Frontier.