Probabilistic denoising for reliable signal extraction in spectroscopy
Abstract
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.
Versions
Related
- Deterministic denoising of long-duration gravitational-wave signal candidates with α-(de)blending
- Extraction of spectral densities from lattice correlators: decoupling signal from noise
- Signal selection and model-independent extraction of pionless charged-current muon neutrino cross section using double-differential kinematic imbalance observables on carbon and oxygen with the T2K experiment
- Accelerating noisy variational quantum algorithms with physics-informed denoising networks
- Breakdown of Local Denoising as Semantic Speciation
BibTeX
@misc{kim2026probabilistic,
title = {{Probabilistic denoising for reliable signal extraction in spectroscopy}},
author = {Younsik Kim and Changyoung Kim},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.07819},
eprint = {2605.07819},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.07819},
}
RIS
TY - UNPB
TI - Probabilistic denoising for reliable signal extraction in spectroscopy
AU - Younsik Kim
AU - Changyoung Kim
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2605.07819
UR - https://arxiv.org/abs/2605.07819
AB - 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.
ER -