Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.18511 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914578418368512 |
|---|---|
| author | Martin-Calle, David Llamas, Cesar Alvarez Ros, Vincent Motto- Dujardin, Christophe Margueritat, Jérémie Rodney, David |
| author_facet | Martin-Calle, David Llamas, Cesar Alvarez Ros, Vincent Motto- Dujardin, Christophe Margueritat, Jérémie Rodney, David |
| contents | A lightweight and reproducible denoising pipeline for high-throughput Raman spectroscopy is presented. The approach relies on a one-dimensional convolutional autoencoder trained using a Noise2Noise strategy, requiring neither external spectral libraries nor high signal-to-noise reference spectra for training. From a reduced training subset composed of repeated short-exposure acquisitions, the model learns to reconstruct Raman spectra while efficiently suppressing stochastic noise. The method is evaluated on a heterogeneous mineral sample, using both quantitative spectral fidelity metrics (RMSE, SNR, SSIM) and task-oriented criteria based on unsupervised K-means classification. Results demonstrate that integration times as short as 5 ms per spectrum, which are typically insufficient for reliable interpretation, yield denoised spectra with high fidelity to the reference data while preserving chemically coherent maps. This work provides a practical trade-off between spectral quality and acquisition speed, enabling fast, adaptable Raman workflows compatible with routine laboratory use. It also offers a transferable framework for other one-dimensional spectroscopic modalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18511 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman Spectroscopy Martin-Calle, David Llamas, Cesar Alvarez Ros, Vincent Motto- Dujardin, Christophe Margueritat, Jérémie Rodney, David Artificial Intelligence Materials Science Signal Processing A lightweight and reproducible denoising pipeline for high-throughput Raman spectroscopy is presented. The approach relies on a one-dimensional convolutional autoencoder trained using a Noise2Noise strategy, requiring neither external spectral libraries nor high signal-to-noise reference spectra for training. From a reduced training subset composed of repeated short-exposure acquisitions, the model learns to reconstruct Raman spectra while efficiently suppressing stochastic noise. The method is evaluated on a heterogeneous mineral sample, using both quantitative spectral fidelity metrics (RMSE, SNR, SSIM) and task-oriented criteria based on unsupervised K-means classification. Results demonstrate that integration times as short as 5 ms per spectrum, which are typically insufficient for reliable interpretation, yield denoised spectra with high fidelity to the reference data while preserving chemically coherent maps. This work provides a practical trade-off between spectral quality and acquisition speed, enabling fast, adaptable Raman workflows compatible with routine laboratory use. It also offers a transferable framework for other one-dimensional spectroscopic modalities. |
| title | A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman Spectroscopy |
| topic | Artificial Intelligence Materials Science Signal Processing |
| url | https://arxiv.org/abs/2605.18511 |