Science and Technology Science and Technology
Wed, January 15, 2025

AI predicts properties of molten salts for modeling safer and more sustainable nuclear power reactors


Published on 2025-01-15 17:02:20 - MSN
  Print publication without navigation

  • Researchers from Skoltech and the Institute of High Temperature Electrochemistry of UB RAS have developed and tested a model based on machine learning that predicts the properties of molten salts. These compounds are already used in metallurgy and hold promise for resolving the problem of mounting nuclear waste.

The article from MSN discusses how researchers at the University of Wisconsin-Madison are using artificial intelligence (AI) to predict the properties of molten salts, which could revolutionize nuclear power reactors. Molten salts are considered for their potential in safer, more efficient, and sustainable nuclear reactors due to their ability to operate at high temperatures, lower pressure, and their capacity to serve both as coolant and fuel. The AI model, developed by Professor Dane Morgan and his team, uses machine learning to analyze the chemical composition of molten salts, predicting their melting points, viscosity, and thermal conductivity. This predictive capability reduces the need for extensive experimental testing, thereby accelerating the development of new reactor designs. The AI's predictions are based on a database of known salt properties, allowing for the design of salts with optimal characteristics for nuclear applications, potentially leading to advancements in energy production that are both safer and more environmentally friendly.

Read the Full MSN Article at:
[ https://www.msn.com/en-us/science/chemistry/ai-predicts-properties-of-molten-salts-for-modeling-safer-and-more-sustainable-nuclear-power-reactors/ar-AA1xgD2v ]
Contributing Sources