# Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data

arXiv: https://arxiv.org/abs/2001.10908 · HTML: https://mlsanity.com/paper/2001.10908/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2020.

## Built on by (most cited first, 7 of 7)

- [Deep learning-based statistical noise reduction for multidimensional spectral data](https://mlsanity.com/paper/2107.00844/) (2021)
- [Denoising and feature extraction in photoemission spectra with variational auto-encoder neural networks](https://mlsanity.com/paper/2203.07537/) (2022)
- [Transfer Learning Application of Self-supervised Learning in ARPES](https://mlsanity.com/paper/2208.10893/) (2022)
- [Spectroscopic data de-noising via training-set-free deep learning method](https://mlsanity.com/paper/2210.10494/) (2022)
- [Removing grid structure in angle-resolved photoemission spectra via deep learning method](https://mlsanity.com/paper/2210.11200/) (2022)
- [A simulation-based training framework for machine-learning applications in ARPES](https://mlsanity.com/paper/2508.15983/) (2025)
- [Training-set-free two-stage deep learning for spectroscopic data de-noising](https://mlsanity.com/paper/2402.18830/) (2024)

## Abstract (arXiv)

Two dimensional (2D) peak finding is a common practice in data analysis for physics experiments, which is typically achieved by computing the local derivatives. However, this method is inherently unstable when the local landscape is complicated, or the signal-to-noise ratio of the data is low. In this work, we propose a new method in which the peak tracking task is formalized as an inverse problem, thus can be solved with a convolutional neural network (CNN). In addition, we show that the underlying physics principle of the experiments can be used to generate the training data. By generalizing the trained neural network on real experimental data, we show that the CNN method can achieve comparable or better results than traditional derivative based methods. This approach can be further generalized in different physics experiments when the physical process is known.