Machine learning reveals the secrets of metal alloys

The concept of short-range ordering - the arrangement of atoms over short distances - has been little researched in materials science. In recent years, interest in it has increased, as it is crucial for the development of high-performance alloys - for example, particularly stable or heat-resistant materials.

However, the exact determination of the atomic arrangement is extremely complex and has so far required elaborate laboratory experiments or computer simulations. Two doctoral students at the Massachusetts Institute of Technology (MIT) are now using machine learning to precisely determine the chemical arrangements in alloys. 

Thanks to this new approach, researchers can gain detailed insights into the atomic structures of materials. These findings open up new possibilities for the targeted development of alloys with customized properties. This offers enormous potential for industries such as aerospace, biomedicine and electronics.