AI could help PNNL pack more nuclear waste into glass

[Marlin]

AI could help PNNL pack more nuclear waste into glass

https://www.tricitiesbusinessnews.com/articles/pnnl-nuclear-waste-glass

[Core Content]

Source: tricitiesbusinessnews.com.

Pacific Northwest National Laboratory researchers developed artificial intelligence models to optimize the vitrification of nuclear waste. By analyzing waste composition, the models recommend specific additive recipes to increase waste loading in glass. This process aims to improve the efficiency of immobilization operations at the Hanford site and other facilities.

Increasing waste loading by even small percentages can reduce long-term cleanup costs by hundreds of millions of dollars. Because Hanford waste varies significantly between batches, the speed of machine learning provides a tool to maintain glass durability while maximizing throughput. Future applications may address high-level waste challenges to prevent melter plugging.

With the help of artificial intelligence, research from scientists at the Pacific Northwest National Laboratory in Richland could help optimize the vitrification of nuclear waste at Hanford and other nuclear sites.

PNNL's work in increasing the "waste loading" of glass could help the Hanford site and other sites around the country to process waste more efficiently, saving money over time.

While Hanford's Waste Treatment and Immobilization Plant, also known as WTP or the vit plant, is responsible for turning the site's nuclear waste into glass, PNNL plays a support role for the facility, developing algorithms, new technologies and troubleshooting.

Read the full article at tricitiesbusinessnews.com:
https://www.tricitiesbusinessnews.com/articles/pnnl-nuclear-waste-glass