Automated structure discovery for Tip Enhanced Raman Spectroscopy
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911463048740864 |
|---|---|
| author | Sethi, Harshit Junttila, Markus Silveira, Orlando J Foster, Adam S |
| author_facet | Sethi, Harshit Junttila, Markus Silveira, Orlando J Foster, Adam S |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19932 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Automated structure discovery for Tip Enhanced Raman Spectroscopy Sethi, Harshit Junttila, Markus Silveira, Orlando J Foster, Adam S Materials Science 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. |
| title | Automated structure discovery for Tip Enhanced Raman Spectroscopy |
| topic | Materials Science |
| url | https://arxiv.org/abs/2602.19932 |