SRNL Harnesses AI to Tackle Environmental Challenges, Cut Cleanup Costs

AIKEN, S.C. — Researchers at Savannah River National Laboratory (SRNL) are supporting the U.S. Department of Energy’s (DOE) Genesis Mission by employing artificial intelligence (AI) and machine learning to tackle complex environmental challenges, which can significantly reduce costs and improve efficiency in the DOE Office of Environmental Management’s cleanup.

Announced in late 2025, the Genesis Mission seeks to revolutionize the scientific process by integrating AI. Earlier this month, the Trump administration unveiled 26 initial research challenges under the mission, including one focused on transforming nuclear cleanup and restoration. With decades of experience in environmental monitoring and a proven track record of integrating advanced technologies into large-scale cleanup efforts, SRNL is uniquely positioned to tackle this challenge.

SRNL is advancing AI Accelerated Strategies and Solutions in Environmental Technology (AI-ASSET), an initiative built upon the successful Advanced Long-Term Environmental Monitoring Systems (ALTEMIS) project. By deploying a smart sensor network, ALTEMIS transforms raw soil and water data into actionable insights that forecast exactly how pollutants migrate through the environment. In doing so, long term monitoring can be performed at a fraction of the cost.

"SRNL is leading a paradigm shift in long term environmental monitoring by bridging the lab’s deep-rooted expertise with the precision of AI and machine learning," said Eric Pierce, associate laboratory director at SRNL. "This innovation enables us to tackle some of the Department of Energy’s most complex cleanup challenges more efficiently while dramatically reducing costs."

ALTEMIS, which SRNL developed over the course of about 15 years, has been used at a contaminated groundwater plume at Savannah River Site. AI-ASSET uses AI and machine learning technology to make ALTEMIS useable at other contaminated sites throughout the DOE complex. These sites have their own specific environmental conditions and unique contaminant data, which creates applicability challenges.

“What we want to do is shorten that time span such that a site could get ALTEMIS up and running within a year, if not under a year,” said SRNL scientist Tom Danielson. “To achieve this, AI is being brought to bear. AI and machine learning tools such as generative AI and large language models are being used to tailor the approach on a site-specific basis.”

The AI and machine learning software being developed by SRNL scientist Alejandro De La Noval can hopefully transition the technology from groundwater projects to monitoring contamination at facilities. The AI-ASSET team hopes to deploy the system at different sites around DOE complex. International sites are also targets for AI-ASSET deployment in the near future, making it applicable across the globe.

Read more about SRNL’s AI and machine learning efforts in the winter edition of Matter Magazine.

-Contributors: Kent Cubbage, LJ Gay