AI Insight
Researchers developed a machine learning framework using ResNet18 convolutional neural networks to classify the handedness of chiral metal surfaces from two types of images: atomic structure models and Fermi surface projections from photoemission spectroscopy. The system achieved 73% accuracy on atomic models but 99% accuracy on Fermi surface projections, demonstrating that surface chirality is more reliably encoded in momentum-space electronic patterns than in real-space atomic geometry. The method successfully transferred to experimental synchrotron data after minimal fine-tuning, establishing a practical tool for characterizing chiral surfaces relevant to catalysis and spintronics.
Why it matters
This work provides the first consistent experimental method to determine the handedness of chiral metal surfaces, which are important for enantiospecific catalysis, molecular sensing, and spintronic devices. The finding that electronic structure preserves chirality information better than atomic geometry has direct implications for understanding chiral-induced spin selectivity effects in realistic, disorder-prone metal surfaces.
arXiv:2606.13144v1 Announce Type: cross
Abstract: Intrinsically chiral metal surfaces, where handedness arises from the asymmetric step-kink-terrace topology of high-Miller-index planes, are model systems for enantiospecific catalysis, sensing, and spintronics. Yet, no consistent method exists to classify their handedness directly from experimental observables. We report a dual-domain machine learning framework that decodes crystallographic surface chirality from two independent image representations: atomic structure models in real space and simulated momentum-resolved photoemission maps of the Fermi surface projections in reciprocal space. ResNet18, a deep convolutional neural network, fine-tuned on a database of labeled images achieves ~73% classification accuracy on atomic models and ~99% on Fermi surface projections. We show that the latter transfers directly to synchrotron-acquired experimental images after fine-tuning on just two labeled frames. We identify a working correspondence between the two representations: just as the kink site geometry fixes the orientation of crystallographic planes in real space, the surface normal position in a momentum-resolved photoemission map anchors the orientation of the Fermi surface polygons in reciprocal space. It is precisely this relative orientation that encodes handedness into the map topology with high accuracy. The pronounced difference in accuracy shows that handedness is more readily recovered from the momentum-space electronic pattern than from the local atomic geometry of the kinked surface. This finding has direct implications for the disorder resilience of geometric chiral-induced spin selectivity (CISS) at realistic metal surfaces.