Coordination-Layer Engineering of Pt Single Atoms on h‑BN for Propane Dehydrogenation via a p‑Band Descriptor Validated by Multiscale Modeling and Knowledge-Informed Machine Learning

Abstract

Single-atom catalysts promise maximal metal and site efficiency, yet predictable bidirectional electronic control remains elusive because most anchoring strategies enforce monotonic charge transfer. The rational design of single-atom catalysts (SACs) demands predictive electronic descriptors that quantitatively link coordination environment to catalytic activity. Here, we establish the p-band center of the first coordination shell (ε_p) as a universal descriptor for electronically tuning Pt single atoms supported on hexagonal boron nitride (h-BN). Through density functional theory calculations, microkinetic modeling, neural network, and SISSO symbolic regression, we uncover a striking bipolar regulation mechanism: carbon doping in the coordination sphere monotonically passivates cationic Pt sites at boron vacancies (Pt/VB) while systematically activating anionic Pt sites at nitrogen vacancies (Pt/VN). This seemingly paradoxical behavior originates from the context-dependent electronic duality of carbon functioning as an electron donor relative to nitrogen yet as an acceptor relative to boron-which drives ε_p in opposite directions across the two vacancy families. The ε_p descriptor governs p-d hybridization strength, which in turn controls transition-state stabilization through metal-support covalent bonding, establishing a mechanistic chain: deep p-band, strong p-d hybridization, enhanced Pt-support bonding in transition state, and low activation barrier. Reactor-scale simulations translate this electronic optimization into a ~1.8-fold difference in propylene yield. To rigorously validate descriptor transferability under sparse, temperature-resolved data, we introduce PhysFormer, a physics-informed neural network that factorizes intrinsic activity and temperature response and SISSO symbolic regression, which identifies ε_p as an irreducible component of the structure-activity relationship in both vacancy families. This work establishes a descriptor-driven and physically constrained learning framework for programmable SAC design via coordination-layer engineering.