The Scientific Discovery through Advanced Computing institute will focus on making scientific machine learning accessible to domain scientists.

The Genesis Mission will mobilize the Department of Energy’s 17 National Laboratories, industry, and academia to build an integrated discovery platform.

An award-winning computing method called poly-streaming accelerates the analysis of massive datasets while using limited memory.

PNNL researchers developed a new computational workflow to study day-to-night gene expression dynamics of cyanobacterium in real time.

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

Predicting how organisms’ characteristics respond to not only their genes, but also their environments (a nascent field called predictive phenomics), is extraordinarily challenging. Researchers at PNNL are using AI to tackle that challenge.

As Laboratory Director Steve Ashby pens his last monthly column, he highlights PNNL’s accomplishments with pride and gratitude.

PNNL researchers have found yet another way to turn trash into treasure: using algal biochar, a waste production from hydrothermal liquefaction, as a supplementary material for cement.

Researchers are uncovering the secrets of a fast-acting molecular messaging network that helps determine how the genetic code plays out.

Micron and PNNL co-design the Crete computer system, delivering a new memory architecture for data-intensive scientific computing and AI applications.

Three research teams led by PNNL organizers achieve journal publications following the Mathematics Research Communities program.

PNNL showcased its expertise in AI, machine learning, and related domains at the International Conference on Machine Learning.

Alex Beliaev, a biologist at PNNL, was named a Society for Industrial Microbiology and Biotechnology fellow.

Expanding the nation’s largest wind power plant time series database; helping grid planners navigate a resilient energy future with better data.

PNNL researchers have published their paper, “Introducing Molecular Hypernetworks for Discovery in Multidimensional Metabolomics Data,” in the Journal of Proteome Research.

PNNL is hosting a scientific conference focused directly on understanding and predicting the collection of an organism’s traits.

Researchers can now quantify uncertainty in trained AI models aimed at solving difficult chemistry, biology and materials science problems.

Researchers have created an algorithm that slashes the calculations necessary to prepare and customize data for quantum computing.

Circadian rhythms of blue-green microbes offer new window into predictive phenomics—how to predict and control the traits of an organism.

Researchers at PNNL are pursuing new approaches to understand, predict and control the phenome—the collection of biological traits within an organism shaped by its genes and interactions with the environment.