Partitioning measured ice nucleating particle concentrations into individual particle types leads to a better understanding of the sources and model representations of these particles.
Researchers from Pacific Northwest National Laboratory created and embedded a physics-informed deep neural network that can learn as it processes data.
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.
Assessing observed weather conditions that support or suppress the growth of clouds into deep precipitating storms during the Cloud, Aerosol, and Complex Terrain Interactions experiment.
Performing closure studies using aerosol size, aerosol composition, and cloud condensation nuclei measurements of mixed aerosol from the Southern Great Plains region.
A PNNL-developed computational framework accurately predicts the thermomechanical history and microstructure evolution of materials designed using solid phase processing, allowing scientists to custom design metals with desired properties.
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.
Research published in Journal of Manufacturing Processes demonstrates innovative single-step method to manufacture oxide dispersion strengthened copper materials from powder.
Secondary organic aerosol formation from monoterpenes is more strongly influenced by oxidant and monoterpene structure than by nitric oxides and hydroperoxy radical concentrations.
Repeated aircraft measurements over central Oklahoma allow researchers to better understand the spatial variability of aerosol properties that affect cloud evolution.
