- Physical Review Journals
All JournalsPhysics Magazine

PRX Intelligence

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Automated Structure Discovery for Tip-Enhanced Raman Spectroscopy

Harshit Sethi1, Markus Junttila1, Orlando J. Silveira1,*, and Adam S. Foster1,2,†

  • 1Department of Applied Physics, Aalto University, Helsinki FI-02150, Finland
  • 2WPI Nano Life Science Institute (WPI-NanoLSI), Kanazawa University, Kakuma-machi, Kanazawa 920-1192, Japan

  • *Contact author: orlando.silveirajunior@aalto.fi
  • †Contact author: adam.foster@aalto.fi
PDF

PRX Intelligence 1, 013023 – Published 24 September, 2026

DOI: https://doi.org/10.1103/8k25-7jtd

Abstract

Tip-Enhanced Raman Spectroscopy (TERS) provides nanoscale chemical fingerprints alongside high-resolution topographic mapping of molecules, offering a powerful tool for materials discovery. However, TERS image datasets are challenging to interpret and typically demand time-consuming, computationally intensive quantum-chemistry calculations. To overcome this problem, we present an encoder-decoder model trained and evaluated on simulated TERS images of planar molecules, enabling direct prediction of molecular structures from spectral simulated data with high accuracy. Our approach demonstrates the feasibility of automating molecular structure identification from TERS images, bypassing traditional manual analysis. These findings provide a foundation for extending machine learning methods to experimental TERS datasets, potentially accelerating molecular discovery by integrating nanoscale spectroscopy with automated computational analysis.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (56)

  1. F. Mohn, J. Repp, L. Gross, G. Meyer, M. S. Dyer, and M. Persson, Reversible bond formation in a gold-atom–organic-molecule complex as a molecular switch, Phys. Rev. Lett. 105, 266102 (2010).
  2. P. Hapala, G. Kichin, C. Wagner, F. S. Tautz, R. Temirov, and P. Jelínek, Mechanism of high-resolution STM/AFM imaging with functionalized tips, Phys. Rev. B 90, 085421 (2014).
  3. K. Sun, O. J. Silveira, Y. Ma, Y. Hasegawa, M. Matsumoto, S. Kera, O. Krejčí, A. S. Foster, and S. Kawai, On-surface synthesis of disilabenzene-bridged covalent organic frameworks, Nat. Chem. 15, 136 (2023).
  4. N. Oinonen, A. V. Yakutovich, A. Gallardo, M. Ondráček, P. Hapala, and O. Krejčí, Advancing scanning probe microscopy simulations: A decade of development in probe-particle models, Comput. Phys. Commun. 305, 109341 (2024).
  5. L. Gross, F. Mohn, N. Moll, P. Liljeroth, and G. Meyer, The chemical structure of a molecule resolved by atomic force microscopy, Science 325, 1110 (2009).
  6. L. Gross, F. Mohn, N. Moll, B. Schuler, A. Criado, E. Guitián, D. Peña, A. Gourdon, and G. Meyer, Bond-order discrimination by atomic force microscopy, Science 337, 1326 (2012).
  7. F. Schulz, J. Ritala, O. Krejčí, A. P. Seitsonen, A. S. Foster, and P. Liljeroth, Elemental identification by combining atomic force microscopy and Kelvin probe force microscopy, ACS Nano 12, 5274 (2018).
  8. E. Abbe Hon, VII.—On the estimation of aperture in the microscope, J. R. Microsc. Soc. 1, 388 (1881).
  9. T. Itoh, M. Procházka, Z.-C. Dong, W. Ji, Y. S. Yamamoto, Y. Zhang, and Y. Ozaki, Toward a new era of SERS and TERS at the nanometer scale: From fundamentals to innovative applications, Chem. Rev. 123, 1552 (2023).
  10. A. B. Zrimsek, N. Chiang, M. Mattei, S. Zaleski, M. O. McAnally, C. T. Chapman, A.-I. Henry, G. C. Schatz, and R. P. Van Duyne, Single-molecule chemistry with surface- and tip-enhanced Raman spectroscopy, Chem. Rev. 117, 7583 (2017).
  11. B. Yang, G. Chen, A. Ghafoor, Y.-F. Zhang, X.-B. Zhang, H. Li, X.-R. Dong, R.-P. Wang, Y. Zhang, Y. Zhang, and Z.-C. Dong, Chemical enhancement and quenching in single-molecule tip-enhanced Raman spectroscopy, Angew. Chem. Int. Ed. 62, e202218799 (2023).
  12. J. Lee, K. T. Crampton, N. Tallarida, and V. A. Apkarian, Visualizing vibrational normal modes of a single molecule with atomically confined light, Nature (London) 568, 78 (2019).
  13. S. Jiang, X. Zhang, Y. Zhang, C. Hu, R. Zhang, Y. Zhang, Y. Liao, Z. J. Smith, Z. Dong, and J. G. Hou, Subnanometer-resolved chemical imaging via multivariate analysis of tip-enhanced Raman maps, Light Sci. Appl. 6, e17098 (2017).
  14. T. Kumagai, K. Miwa, and B. Cirera, Point-contact tip-enhanced Raman spectroscopy: Picoscale light–matter interactions within plasmonic cavities, Nano Lett. 25, 15449 (2025).
  15. R. C. de Campos Ferreira, B. Cirera, J. Doležal, Á. G. de Roa, A. Sagwal, P. Kahan, R. Canales, F. Aguilar-Galindo, M. Švec, and P. Merino, Adsorption-driven symmetry lowering in single molecules revealed by Ångstrom-scale tip-enhanced Raman imaging, J. Am. Chem. Soc. 148, 9375 (2026).
  16. C. Höppener, J. Aizpurua, H. Chen, S. Gräfe, A. Jorio, S. Kupfer, Z. Zhang, and V. Deckert, Tip-enhanced Raman scattering, Nat. Rev. Methods Primers 4, 47 (2024).
  17. Y. Zhang, Z.-C. Dong, and J. Aizpurua, Theoretical treatment of single-molecule scanning Raman picoscopy in strongly inhomogeneous near fields, J. Raman Spectrosc. 52, 296 (2021).
  18. S. Duan, G. Tian, Y. Ji, J. Shao, Z. Dong, and Y. Luo, Theoretical modeling of plasmon-enhanced Raman images of a single molecule with subnanometer resolution, J. Am. Chem. Soc. 137, 9515 (2015).
  19. Y. Zhang, R. Esteban, J. Cui, and J. Aizpurua, Software to implement simulations of Raman spectra of single-molecules in an inhomogeneous field, 2023, https://doi.org/10.20350/digitalCSIC/15303.
  20. Y. Litman, F. P. Bonafé, A. Akkoush, H. Appel, M. Rossi, First-principles simulations of tip enhanced Raman scattering reveal active role of substrate on high-resolution images, J. Phys. Chem. Lett. 14, 6850 (2023).
  21. X. Chen, P. Liu, Z. Hu, and L. Jensen, High-resolution tip-enhanced Raman scattering probes sub-molecular density changes, Nat. Commun. 10, 2567 (2019).
  22. F. Qiu, Z.-Y. Gong, D. Cao, C. Song, G. Tian, S. Duan, and Y. Luo, Optical images of molecular vibronic couplings from tip-enhanced fluorescence excitation spectroscopy, JACS Au 2, 150 (2022).
  23. H.-Z. Yu, R.-L. Han, D. Chu, Y. Li, X.-R. Dong, Y. Zhang, L. Wang, Y. Song, C.-K. Wang, Z. Xie, and S. Duan, Theoretical prediction for monitoring Jahn-Teller vibrational evolution using real-space tip-enhanced Raman imaging, Nat. Commun. 17, 1132 (2026).
  24. K. Brezina, Y. Litman, and M. Rossi, Tip-enhanced Raman images of realistic systems through ab initio modeling, ACS Nano 20, 5550 (2026).
  25. X. Chen, S. Xu, S. Shabani, Y. Zhao, M. Fu, A. J. Millis, M. M. Fogler, A. N. Pasupathy, M. Liu, and D. N. Basov, Machine learning for optical scanning probe nanoscopy, Adv. Mater. 35, 2109171 (2023).
  26. N. Kumar, L.-Q. Zheng, A. J. Pollard, A. J. Wain, and R. Zenobi, Nanoscale chemical analysis of heterogeneous catalysts using tip-enhanced Raman spectroscopy, Chem. Rev. 126, 2653 (2026).
  27. M. Ziatdinov, A. Maksov, and S. V. Kalinin, Learning surface molecular structures via machine vision, npj Comput. Mater. 3, 31 (2017).
  28. A. Khan, C.-H. Lee, P. Y. Huang, and B. K. Clark, Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images, npj Comput. Mater. 9, 85 (2023).
  29. K. Choudhary, Microscopygpt: Generating atomic-structure captions from microscopy images of 2D materials with vision-language transformers, J. Phys. Chem. Lett. 16, 7028 (2025).
  30. S. V. Kalinin, E. Strelcov, A. Belianinov, S. Somnath, R. K. Vasudevan, E. J. Lingerfelt, R. K. Archibald, C. Chen, R. Proksch, N. Laanait, S. Jesse, Big, deep, and smart data in scanning probe microscopy, ACS Nano 10, 9068 (2016).
  31. Md A. R. Laskar and U. Celano, Scanning probe microscopy in the age of machine learning, APL Mach. Learn. 1, 041501 (2023).
  32. B. Alldritt, P. Hapala, N. Oinonen, F. Urtev, O. Krejci, F. F. Canova, J. Kannala, F. Schulz, P. Liljeroth, and A. S. Foster, Automated structure discovery in atomic force microscopy, Sci. Adv. 6, eaay6913 (2020).
  33. B. Tang, Y. Song, M. Qin, Y. Tian, Z. W. Wu, Y. Jiang, D. Cao, and L. Xu, Machine learning-aided atomic structure identification of interfacial ionic hydrates from AFM images, Natl. Sci. Rev. 10, nwac282 (2023).
  34. N. Oinonen, L. Kurki, A. Ilin, and A. S. Foster, Molecule graph reconstruction from atomic force microscope images with machine learning, MRS Bull. 47, 895 (2022).
  35. L. Kurki, N. Oinonen, and A. S. Foster, Automated structure discovery for scanning tunneling microscopy, ACS Nano 18, 11130 (2024).
  36. F. Priante, N. Oinonen, Y. Tian, D. Guan, C. Xu, S. Cai, P. Liljeroth, Y. Jiang, and A. S. Foster, Structure discovery in atomic force microscopy imaging of ice, ACS Nano 18, 5546 (2024).
  37. J. Carracedo-Cosme, C. Romero-Muñiz, P. Pou, and R. Pérez, Molecular identification from AFM images using the IUPAC nomenclature and attribute multimodal recurrent neural networks, ACS Appl. Mater. Interfaces 15, 22692 (2023).
  38. J. Carracedo-Cosme, R. Pérez, Molecular identification with atomic force microscopy and conditional generative adversarial networks, npj Comput. Mater. 10, 19 (2024).
  39. S. Duan, G. Tian, and Y. Luo, Visualization of vibrational modes in real space by tip-enhanced non-resonant Raman spectroscopy, Angew. Chem. Int. Ed. 55, 1041 (2016).
  40. Y. Li, D. Chu, W. Ma, H.-Z. Yu, Y. Song, C.-K. Wang, S. Duan, and Z. Xie, Visualization of hydrogen isotope exchange in single molecule by tip-enhanced Raman images, J. Chem. Phys. 163, 224310 12 (2025).
  41. N. Oinonen, C. Xu, B. Alldritt, F. F. Canova, F. Urtev, S. Cai, O. Krejčí, J. Kannala, P. Liljeroth, and A. S. Foster, Electrostatic discovery atomic force microscopy, ACS Nano 16, 89 (2022).
  42. M. J. Frisch, G. W. Trucks, H. B. Schlegel, G. E. Scuseria, M. A. Robb, J. R. Cheeseman, G. Scalmani, V. Barone, G. A. Petersson, H. Nakatsuji, et al., Gaussian ̃16 Revision C.01 (Gaussian Inc., Wallingford, CT, 2016).
  43. V. Badrinarayanan, A. Kendall, and R. Cipolla, SegNet: A deep convolutional encoder-decoder architecture for image segmentation, IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481 (2017).
  44. O. Oktay, J. Schlemper, L. L. Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N. Y. Hammerla, B. Kainz, B. Glocker, and D. Rueckert, Attention U-Net: Learning where to look for the pancreas, in Medical Imaging with Deep Learning (OpenReview Foundation, Amherst, Massachusetts, 2018), https://openreview.net/forum?id=Skft7cijM.
  45. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, in Proceedings of the 3rd International Conference on Learning Representations (ICLR, San Diego, 2015).
  46. L. R. Dice, Measures of the amount of ecologic association between species, Ecology 26, 297 (1945).
  47. T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, Optuna: A next-generation hyperparameter optimization framework, in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM Press, New York, NY, 2019).
  48. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, et al., PyTorch: An imperative style, high-performance deep learning library, in Advances in Neural Information Processing Systems 32, Vancouver, BC (Curran Associates, Inc., 2019), pp. 8024–8035.
  49. Y. Tian, G. Cheng, G. Shen, X. Zhu, J. Xu, A-l. Jia, Z. Liu, H. Du, S. Tan, and B. Wang, Autonomous single-molecule chemical identification with an AI-enabled STM-TERS platform, Precis. Chem. (2026), doi:10.1021/prechem.6c00036.
  50. J. Cui, Y. Zhang, Y. Zhang, Y. Luo, and Z.-C. Dong, TERS-ABNet: A deep learning approach for automated single-molecule structure reconstruction with atomic precision from TERS mapping, arXiv:2603.21579.
  51. H. Sethi, M. K. Junttila, O. Silveira, A. Foster, Training dataset for SMARTERS: A machine learning model for automated structure discovery in tip-enhanced Raman spectroscopy [Data set], Zenodo, 2026, https://doi.org/10.5281/zenodo.18768437.
  52. H. Sethi, M. K. Junttila, O. Silveira, A. Foster, SMARTERS (structural machine learning for high-resolution tip-enhanced Raman spectroscopy), Github, 2026, https://github.com/SINGROUP/SMARTERS.
  53. O. Ronneberger, P. Fischer, and T. Brox, U-Net: Convolutional networks for biomedical image segmentation, in Medical Image Computing and Computer-Assisted Intervention (MICCAI) (Springer, Cham, Switzerland, 2015), pp. 234–241.
  54. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, in Advances in Neural Information Processing Systems 30, Long Beach, California (Curran Associates, Inc., 2017), pp. 5998–6008.
  55. T. Lindeberg, Feature detection with automatic scale selection, Int. J. Comput. Vision 30, 79 (1998).
  56. D. Marr and E. Hildreth, Theory of edge detection, Proc. R. Soc. London, Ser. B Biol. Sci. 207, 187 (1980).

Outline

Information

PRX Intelligence 1, 013023– Published 24 September, 2026
  • Received 25 February 2026
  • Accepted 4 August 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation