PNNL’s software tool brings together artificial intelligence and satellite imagery to help responders assess damage and take action.

Incorporating spatially explicit land characteristics in a global model illustrates the complex effects of applying uniform regional protection assumptions in a global analysis.

The first study modeling the mechanism of hydrated electron formation from aqueous iodide.

A suite of experiments provide insight into how diopside reacts with carbon dioxide to form stable carbonate species.

The diversity and function of organic matter in rivers at a large scale are influenced by factors, such as the types of vegetation covering the land, the energy characteristics, and the breakdown potential of the molecules.

New research reveals enhanced CO2 transport across a polyether ether ketone membrane and water-lean solvent interface

Studying single crystal reactions provides molecular-level insight into catalytic processes.

Harnessing machine learning to enhance plant coexistence in a vegetation demographic model.

Simulations show an amorphous intermediate that allows impurities to incorporate into crystallizing calcium carbonate.

Scientists can now generate a protein database directly from proteomics data gathered from a specific soil sample using a digital tool and deep learning computer model called Kaiko.

Researchers from Pacific Northwest National Laboratory created and embedded a physics-informed deep neural network that can learn as it processes data.

Summer is for science! PNNL’s interns are diving into science and technology and getting a front-row view of the research and development of a national laboratory.

Different sources of low-level moisture perturbation can result in differences in the timing and location of a large, modeled storm.

A holistic evaluation of the uncertainty sources that arise from configuring the model to processing the output for global variable-resolution models.

Randomly constructed neural networks can learn how to represent light interacting with atmospheric aerosols accurately at a low computational cost and improve climate modeling capabilities.

A success story of applying convergence testing to detect and address issues of numerical discretization in nonlinear representations of turbulence and clouds.

A crystalline silicate framework forms through a non-classical, multi-step nucleation mechanism based on structurally precise clusters.

A new review describes the insights that may be gained into important electrochemical processes using ion soft landing.

Faced with limited data, researchers at PNNL studied different techniques to improve disease prediction in resource-limited settings.

A new open-source feature tracking package is now available to facilitate advanced model evaluation, model development efforts, and scientific discovery.