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

Researchers identified a new intermediate phase that forms during the crystallization of hydrated aluminum-containing salts.

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.

The amount of radiation in a system influences how fast aggregated boehmite particles dissolve.

PNNL research, featured on the cover of two science journals, describes advancements in using Raman spectrometry for Hanford Site nuclear waste remediation.

Simulations show that pH influences boehmite nanoparticle structure and sorption ability.

Developing a new understanding of the structure of natrophosphate, a complex mineral found in radioactive tank waste at the Hanford Site, by integrating experimental techniques.

PNNL researchers teamed up with SambaNova to enhance artificial intelligence for scientific computing.

The size and concentration of ions influences the aggregation behavior of solutions of boehmite.

PNNL researchers design an artificial intelligence-guided electron microscope in a Laboratory Directed Research and Development study.

The size of the alkali metal within the material influences the crystallization pathway.

Performing a network analysis of forces between particles reveals new insight into shear induced thinning and thickening in non-Newtonian fluids.

IDREAM researchers show that high concentrations of sodium hydroxide significantly impact the molecular and macroscale properties of sodium nitrite solutions.

Researchers in the IDREAM Energy Frontier Research Center unearth new defects during gibbsite crystallization using a multi-instrument approach.

Newly determined energy transfer mechanisms help identify how water releases from and damages irradiated interfaces.

Developing an understanding of how water breaks apart after radiation exposure.

IDREAM researchers use fast force mapping to provide insights into the boehmite interfacial solution structure.

IDREAM researchers assess the potential of photon-in/photon-out XFEL techniques to explore early time reaction steps and ultimately improve nuclear waste processing strategies.

A multi-institutional team has developed a deep learning framework to identify novel molecules as drug candidates.

IDREAM study characterizes chemical species and mechanisms that control aluminum salt and mineral crystallization for nuclear waste retrieval, processing.