Quantum precision reached in modeling molten salt behavior
AI boosts simulations to precisely predict properties of materials for nuclear energy
image: The melting point of lithium chloride can be accurately predicted from simulations by converting liquid salt into a gas (top) and solid crystal into a network of springs (bottom).
Credit: Credit: Luke Gibson/ORNL, U.S. Dept. of Energy
Scientists have developed a new machine learning approach that accurately predicted critical and difficult-to-compute properties of molten salts, materials with diverse nuclear energy applications.
In a Chemical Science article, Oak Ridge National Laboratory researchers demonstrated the ability to rapidly model salts in liquid and solid state with quantum chemical accuracy. Specifically, they looked at thermodynamic properties, which control how molten salts function in high-temperature applications. These applications include dissolving nuclear fuels and improving reliability of long-term reactor operations. The AI-enabled approach was made possible by ORNL’s supercomputer Summit.
“The exciting part is the simplicity of the approach,” said ORNL’s Luke Gibson. “In fewer steps than existing approaches, machine learning gets us to higher accuracy at a faster rate.”
Historically, understanding the broad range of molten salt properties has been expensive and challenging. Large-scale, affordable and high-accuracy modeling can bridge the gap between experiment and simulation, which is crucial to accelerating next-generation reactor design, safety measures and waste management. — Emily Tomlin