Probabilistic denoising for reliable signal extraction in spectroscopy
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911662812954624 |
|---|---|
| author | Kim, Younsik Kim, Changyoung |
| author_facet | Kim, Younsik Kim, Changyoung |
| contents | While deep learning offers powerful capabilities for scientific research, its application is often hindered by a lack of quantitative reliability. To address this, we introduce a probabilistic denoising framework that simultaneously extracts denoised signals and element-wise predictive uncertainties from noisy data. We demonstrate this approach on three-dimensional angle-resolved photoemission spectroscopy data, showing that the model reliably recovers the spectral features of a cuprate superconductor from Poisson-distributed noise with an average count of only 0.02 electrons per voxel. Crucially, we show that these predicted uncertainties can be propagated into subsequent superconducting gap analyses, enabling quantitative parameter extraction with scientifically meaningful error bars. Furthermore, we validate the broad applicability of our approach by successfully extending it to two-dimensional X-ray diffraction data. Ultimately, this approach establishes uncertainty-aware deep learning not merely as a visualization tool, but as a rigorous framework for scientific data analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07819 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Probabilistic denoising for reliable signal extraction in spectroscopy Kim, Younsik Kim, Changyoung Strongly Correlated Electrons Superconductivity Data Analysis, Statistics and Probability While deep learning offers powerful capabilities for scientific research, its application is often hindered by a lack of quantitative reliability. To address this, we introduce a probabilistic denoising framework that simultaneously extracts denoised signals and element-wise predictive uncertainties from noisy data. We demonstrate this approach on three-dimensional angle-resolved photoemission spectroscopy data, showing that the model reliably recovers the spectral features of a cuprate superconductor from Poisson-distributed noise with an average count of only 0.02 electrons per voxel. Crucially, we show that these predicted uncertainties can be propagated into subsequent superconducting gap analyses, enabling quantitative parameter extraction with scientifically meaningful error bars. Furthermore, we validate the broad applicability of our approach by successfully extending it to two-dimensional X-ray diffraction data. Ultimately, this approach establishes uncertainty-aware deep learning not merely as a visualization tool, but as a rigorous framework for scientific data analysis. |
| title | Probabilistic denoising for reliable signal extraction in spectroscopy |
| topic | Strongly Correlated Electrons Superconductivity Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2605.07819 |