# Neural networks trained on synthetically generated crystals can extract structural information from ICSD powder X-ray diffractograms

arXiv: https://arxiv.org/abs/2303.11699 · HTML: https://mlsanity.com/paper/2303.11699/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 44 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [A probabilistic deep learning approach to automate the interpretation of multi-phase diffraction spectra](https://mlsanity.com/paper/2103.16664/) (2021)
- [A universal synthetic dataset for machine learning on spectroscopic data](https://mlsanity.com/paper/2206.06031/) (2022)

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

- [opXRD: Open Experimental Powder X-ray Diffraction Database](https://mlsanity.com/paper/2503.05577/) (2025)
- [MatBind: A Shared Embedding Space for Multimodal Materials Characterization](https://mlsanity.com/paper/2607.08470/) (2026)

## Abstract (arXiv)

Machine learning techniques have successfully been used to extract structural information such as the crystal space group from powder X-ray diffractograms. However, training directly on simulated diffractograms from databases such as the ICSD is challenging due to its limited size, class-inhomogeneity, and bias toward certain structure types. We propose an alternative approach of generating synthetic crystals with random coordinates by using the symmetry operations of each space group. Based on this approach, we demonstrate online training of deep ResNet-like models on up to a few million unique on-the-fly generated synthetic diffractograms per hour. For our chosen task of space group classification, we achieved a test accuracy of 79.9% on unseen ICSD structure types from most space groups. This surpasses the 56.1% accuracy of the current state-of-the-art approach of training on ICSD crystals directly. Our results demonstrate that synthetically generated crystals can be used to extract structural information from ICSD powder diffractograms, which makes it possible to apply very large state-of-the-art machine learning models in the area of powder X-ray diffraction. We further show first steps toward applying our methodology to experimental data, where automated XRD data analysis is crucial, especially in high-throughput settings. While we focused on the prediction of the space group, our approach has the potential to be extended to related tasks in the future.