Select Page

Fulton Schools: In the News

From ancient minerals to new materials: Melting temperature prediction using a graph neural network model

From ancient minerals to new materials: Melting temperature prediction using a graph neural network model

To build the high performance materials needed today, it’s critical to know the precise melting temperatures of various materials. The safety of bridges, jet engines and heat shields for aircraft, for example, depends on knowing the performance limits of materials under environmental stresses.  Now, ASU researchers working with a Brown University researcher have found a way to use artificial intelligence and machine learning to predict the melting temperatures for potentially any compound or chemical formula. The team includes Assistant Professor Qi-Jun Hong and Professor Alexandra Navrotsky, both in the School for Engineering of Matter, Transport and Energy, one of the seven Fulton Schools at ASU. The article is also published in TechCodex, PNAS, Verve Times, Knowledia, Supercomputing Online News, My Droll, Lab Manager, Space Daily and Verified News Explorer Network

ASU Engineering on Facebook