Repository logo

Mapping Atomic-Scale Metal-Molecule Interactions: Salient Feature Extraction through Autoencoding of Vibrational Spectroscopy Data.

Accepted version



Change log


Poppe, Alex 
Griffiths, Jack 
Hu, Shu 
Osadchy, Margarita 


Atomic-scale features, such as step edges and adatoms, play key roles in metal-molecule interactions and are critically important in heterogeneous catalysis, molecular electronics, and sensing applications. However, the small size and often transient nature of atomic-scale structures make studying such interactions challenging. Here, by combining single-molecule surface-enhanced Raman spectroscopy with machine learning, spectra are extracted of perturbed molecules, revealing the formation dynamics of adatoms in gold and palladium metal surfaces. This provides unique insight into atomic-scale processes, allowing us to resolve where such metallic protrusions form and how they interact with nearby molecules. Our technique paves the way to tailor metal-molecule interactions on an atomic level and assists in rational heterogeneous catalyst design.



51 Physical Sciences, 34 Chemical Sciences, 3406 Physical Chemistry, Generic health relevance

Journal Title

J Phys Chem Lett

Conference Name

Journal ISSN


Volume Title


American Chemical Society (ACS)
European Commission Horizon 2020 (H2020) ERC (883703)
Royal Society (URF\R1\211162)
This research has been supported by the European Research Council (ERC) under Horizon 2020 research and innovation programme PICOFORCE (grant agreement no. 883703). B.d.N. acknowledges support from the Royal Society (URF\R1\211162). A.D.P. acknowledges support from VisionMetric Ltd. and IS-Instruments Ltd.