Decoding the Stability of Transition-Metal Alloys with Theory-infused Deep Learning

Abstract

We introduce an interpretable deep learning framework that predicts the cohesive energy of transition-metal alloys (TMAs) by embedding cohesion theory within graph neural networks (GNNs). Beyond accurate prediction of cohesive energy, a key indicator of thermodynamic stability, the model offers mechanistic insights by disentangling energy contributions into physically meaningful components. These data-driven interpretations reveal periodic trends and stability principles governing transition metals. We apply the model to single-atom alloys (SAAs) to assess their thermodynamic resilience against two destabilizing processes: agglomeration (adatom clustering) and segregation (migration into the subsurface). Our analysis shows that these phenomena are governed by distinct physical factors-agglomeration is primarily influenced by localized d-orbital coupling, while segregation is dictated by delocalized effects such as wavefunction renormalization. This model thus serves as an explainable AI tool for understanding and guiding the design of stable TMAs, with implications for catalysis and materials discovery.