A team of researchers at MIT has developed a new method called AutoSurfRecon that uses machine learning to study the surfaces of materials.

This new approach provides more detailed information than traditional methods and eliminates guesswork.

The researchers discovered two new atomic configurations on a material that had been studied for 30 years.

AutoSurfRecon provides dynamic information on how surface properties change over time and estimates all possible variations.

The method has been made freely available for other researchers to use in developing new materials for catalysts, semiconductors, or battery components.

This new strategy has the potential to benefit industries that rely on these materials.

The research has been supported by the U.S. Air Force and the U.S. National Science Foundation.

The studies highlight the potential of machine learning in accelerating materials discovery and design.