# A Pilot Study For Fragment Identification Using 2D NMR and Deep Learning

arXiv: https://arxiv.org/abs/2103.12169 · HTML: https://mlsanity.com/paper/2103.12169/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 49 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 3 of 3)

- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Deep Learning on Small Datasets without Pre-Training using Cosine Loss](https://mlsanity.com/paper/1901.09054/) (2019)
- [Do We Need More Training Data?](https://mlsanity.com/paper/1503.01508/) (2015)

## Built on by (most cited first, 2 of 2)

- [A large-scale foundation model enables simulation-to-real adaptation for nuclear magnetic resonance-based molecular structure analysis](https://mlsanity.com/paper/2606.20756/) (2026)
- [Direct deduction of chemical class from NMR spectra](https://mlsanity.com/paper/2211.03173/) (2022)

## Abstract (arXiv)

This paper presents a method to identify substructures in NMR spectra of mixtures, specifically 2D spectra, using a bespoke image-based Convolutional Neural Network application. This is done using HSQC and HMBC spectra separately and in combination. The application can reliably detect substructures in pure compounds, using a simple network. It can work for mixtures when trained on pure compounds only. HMBC data and the combination of HMBC and HSQC show better results than HSQC alone.