COD Synthetic Powder X-Ray Diffraction (XRD) Patterns: 436,196 Simulated Diffractograms from the Crystallography Open Database
- Provider
- ohlstrom (Hugging Face); structures from the Crystallography Open Database
- License
- CC0-1.0 (source)
- Size
- 7 files
- Stored at
- Hugging Face (https://huggingface.co/datasets/ohlstrom/Crystallography-Open-Database-XRD-Patterns)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Chemistry & Materials
- Source
- https://www.crystallography.net/cod/
About this dataset
Simulated powder X-ray diffraction (PXRD) patterns for every CIF crystal structure in the Crystallography Open Database (COD): 436,196 diffractograms spanning metals, minerals, organic molecular crystals and metal-organic frameworks. Each pattern was computed with the pymatgen XRDCalculator for Cu K-alpha radiation (1.54184 angstrom) over 2-theta 0 to 90 degrees at a 0.02 degree step, giving a 4,500-point intensity vector min-max scaled to [0, 1]. Files are PyTorch .pt dictionaries holding a patterns tensor of shape (N, 4500) and the matching COD CIF filenames, so each pattern links back to its structure at crystallography.net by COD ID. The full set ships with random subsets of 1,000, 10,000, 50,000 and 100,000 patterns for prototyping. No measured diffractograms are included. Use it to train phase identification, crystal system and space group classifiers, or diffraction-to-structure models; load with torch.load. License CC0 1.0, the same as COD. Cite Grazulis et al., Crystallography Open Database, J. Appl. Cryst. 42, 726 (2009), and pymatgen (Ong et al. 2013).
How to load this dataset in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="ohlstrom/Crystallography-Open-Database-XRD-Patterns", filename="COD_xrd_patterns_1000.pt", repo_type="dataset")
print(path)Data structure
Files
Example file: COD_xrd_patterns_1000.pt
Analyze this dataset without downloading it
On Scigantic, COD Synthetic Powder X-Ray Diffraction (XRD) Patterns: 436,196 Simulated Diffractograms from the Crystallography Open Database opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Chemistry & Materials datasets
- MofasaDB: 200,000 Generated Metal-Organic Frameworks from the Mofasa Diffusion Model
- Halide Perovskite Ion Migration MLFF positive iodide vacancy
- Iron Nanoparticle DFT Database: Clusters, Bulk Phases, Surfaces and Liquid Fe (Jana and Caro 2023), ColabFit Conversion
- Open Molecules 2025 (OMol25) 4M Training Subset, ColabFit Conversion
- MassBank 2026.03, open-licence records: 96,949 reference mass spectra of 10,304 compounds as MSP and Parquet
- CoRE MOF 2024: Computation-Ready Experimental Metal-Organic Frameworks (Public SI Subset)
- Open Catalyst 2020 (OC20) S2EF 200K Training Set, ColabFit Conversion
- Stable and Metastable CuInS2 (CIS) Chalcopyrite Polytypes for Solar Cells: DFT Formation Energies (Larsen et al. 2022, Materials Cloud), ColabFit Conversion